breast cancer thesis 2020

• Harvard Medical School
• HMS Theses and Dissertations
• Communities & Collections
• By Issue Date
• FAS Department
• Quick submit
• Waiver Generator
• DASH Stories
• Accessibility
• COVID-related Research

Terms of Use

• Privacy Policy
• By Collections
• By Departments

Targeted Therapies for the Treatment of Metastatic Breast Cancer

Citable link to this page

Collections.

• HMS Theses and Dissertations [537]

Contact administrator regarding this item (to report mistakes or request changes)

•   Hjem
• Universitetet i Stavanger
• Faculty of Health Sciences
• PhD theses (HV)
• Vis innførsel

Discovery and Validation of Biomarkers in Breast Cancer

Egeland, nina gran, doctoral thesis.

Permanent lenke

Utgivelsesdato.

• PhD theses (HV) [50]

Originalversjon

Består av, opphavsrett.

Breast cancer early detection: A phased approach to implementation

Affiliations.

• 1 Perlmutter Cancer Center, Section for Global Health, Division of Health and Behavior, Department of Population Health, New York University Langone Health, New York, New York.
• 2 Department of Surgery, Faculty of Medicine, University of Malaya, Kuala Lumpur, Malaysia.
• 3 Ramsay Sime Darby Health Care, Kuala Lumpur, Malaysia.
• 4 Department of Surgery, University of Pennsylvania, Philadelphia, Pennsylvania.
• 5 The Susan G. Komen Foundation, Washington, District of Columbia.
• 6 Breast Center, Moinhos de Vento Hospital, Porto Alegre, Brazil.
• 7 Department of Breast, Skin, and Soft Tissue Sarcomas Surgery, National Institute of Neoplastic Diseases, Lima, Peru.
• 8 Department of Oncology, Department of Public Health Sciences and Division of Cancer Care and Epidemiology, Queen's University, Kingston, Ontario, Canada.
• 9 International Agency for Research on Cancer, Lyon, France.
• 10 Department of Nursing, University of Panama, Panama City, Panama.
• 11 India Cancer Research Consortium, Delhi, India.
• 12 Unit for Biomedical Cancer Research, National Cancer Institute, National Autonomous University of Mexico, Mexico City, Mexico.
• 13 Xavierian University Oncology Center, San Ignacio University Hospital, Bogota, Colombia.
• 14 Faculty of Medicine, Pontifical Xavierian University, Bogota, Colombia.
• 15 Division of Women's Health, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts.
• 16 Department of Internal Medicine, College of Medicine, The Ohio State University, Columbus, Ohio.
• 17 Breast Surgery, Dubin Breast Center, The Icahn School of Medicine at The Mount Sinai Hospital, New York, New York.
• 18 Department of Health System Design and Global Health, Icahn School of Medicine at The Mount Sinai Hospital.
• 19 Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland.
• 20 Department of Radiology, University of Washington, Seattle, Washington.
• 21 Department of Global Health, University of Washington, Seattle, Washington.
• 22 Health, Nutrition, and Population Global Practice, The World Bank Group, Washington, District of Columbia.
• 23 CONACYT Fellow, National Cancer Institute, Mexico City, Mexico.
• 24 National Center for Oncology, Radiotherapy, and Nuclear Medicine, Accra, Ghana.
• 25 Center for Health Disparities Innovation and Studies, Eastern Michigan University, Ypsilanti, Michigan.
• 26 Reproductive and Child Health Section, Ministry of Health, Community, Ministry of Health, Community Development, Development Gender, Elderly, and Children Dodoma, Children Dodoma, Tanzania.
• 27 Breast Health Global Initiative, Fred Hutchinson Cancer Research Center, Seattle, Washington.
• 28 Department of Medicine, University of Washington, Seattle, Washington.
• 29 Department of Surgery, University of Washington, Seattle, Washington.
• PMID: 32348566
• PMCID: PMC7237065
• DOI: 10.1002/cncr.32887

When breast cancer is detected and treated early, the chances of survival are very high. However, women in many settings face complex barriers to early detection, including social, economic, geographic, and other interrelated factors, which can limit their access to timely, affordable, and effective breast health care services. Previously, the Breast Health Global Initiative (BHGI) developed resource-stratified guidelines for the early detection and diagnosis of breast cancer. In this consensus article from the sixth BHGI Global Summit held in October 2018, the authors describe phases of early detection program development, beginning with management strategies required for the diagnosis of clinically detectable disease based on awareness education and technical training, history and physical examination, and accurate tissue diagnosis. The core issues address include finance and governance, which pertain to successful planning, implementation, and the iterative process of program improvement and are needed for a breast cancer early detection program to succeed in any resource setting. Examples are presented of implementation, process, and clinical outcome metrics that assist in program implementation monitoring. Country case examples are presented to highlight the challenges and opportunities of implementing successful breast cancer early detection programs, and the complex interplay of barriers and facilitators to achieving early detection for breast cancer in real-world settings are considered.

Keywords: breast cancer; breast cancer early detection; metrics; phased implementation; resource stratification.

© 2020 American Cancer Society.

Publication types

• Research Support, N.I.H., Extramural
• Research Support, Non-U.S. Gov't
• Breast Neoplasms / diagnosis*
• Delivery of Health Care
• Developing Countries
• Early Detection of Cancer / economics
• Early Detection of Cancer / methods*
• Global Health
• Health Plan Implementation / economics
• Health Plan Implementation / methods*
• Practice Guidelines as Topic
• Socioeconomic Factors

Grants and funding

• SAC170082/KOMEN/Susan G. Komen/United States
• 1R13CA224776-01A1/CA/NCI NIH HHS/United States
• 001/WHO_/World Health Organization/International
• R13 CA224776/CA/NCI NIH HHS/United States
• GSP18BHGI001/KOMEN/Susan G. Komen/United States

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• Healthcare (Basel)

Breast Cancer Dataset, Classification and Detection Using Deep Learning

Muhammad shahid iqbal.

1 Department of Computer Science and Information Technology, Women University AJK, Bagh 12500, Pakistan

Waqas Ahmad

2 Higher Education Department Govt, AJK, Mirpur 10250, Pakistan

Roohallah Alizadehsani

3 Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, VIC 3216, Australia

Sadiq Hussain

4 Examination Branch, Dibrugarh University, Dibrugarh 786004, India

Rizwan Rehman

5 Centre for Computer Science and Applications, Dibrugarh University, Dibrugarh 786004, India

Associated Data

Not applicable.

Incorporating scientific research into clinical practice via clinical informatics, which includes genomics, proteomics, bioinformatics, and biostatistics, improves patients’ treatment. Computational pathology is a growing subspecialty with the potential to integrate whole slide images, multi-omics data, and health informatics. Pathology and laboratory medicine are critical to diagnosing cancer. This work will review existing computational and digital pathology methods for breast cancer diagnosis with a special focus on deep learning. The paper starts by reviewing public datasets related to breast cancer diagnosis. Additionally, existing deep learning methods for breast cancer diagnosis are reviewed. The publicly available code repositories are introduced as well. The paper is closed by highlighting challenges and future works for deep learning-based diagnosis.

1. Introduction

Computational pathology (CP) has the potential to improve clinical workflow efficiency and diagnostic quality thanks to information integration and advanced digital communication networks [ 1 ]. CP is accompanied by several challenges, such as efficient data fusion, limited processing capabilities, and compliance with ethical practices [ 2 ].

Over 2 million women were examined for breast cancer in 2018, among whom approximately 0.6 million died worldwide. Most intrusive breast cancer diseases are chemical receptor-positive [ 3 ]. Chemical therapies targeting the trauma center flagging pathway often help patients with chemical receptor-positive tumors [ 4 ]. After delicately segmenting a patient’s example onto magnifying instrument slides for staining, a pathologist draws a visual conclusion based on hematoxylin and eosin (H&E) staining, and subatomic marker-explicit stains are used for confirmation and subtyping. Trauma centers are identified using atomic ImmunoHistoChemistry (IHC). However, IHC staining is both time-consuming and expensive [ 5 , 6 ]. Moreover, test quality can vary significantly due to differences in tissue, the skill level of the expert taking the tissue sample, and specialist ability levels [ 7 , 8 ]. Finally, pathologists’ decisions are prone to error [ 9 ]. These factors contribute to misdiagnosis. About 20% of current IHC-based trauma center and PR test results are incorrect [ 9 , 10 ], putting patients at risk of receiving subpar treatment. Recent research has shown that emergency room tests can be resolved using morphological stains. However, these studies rely on single-focus tissue microarray datasets (TMAs) [ 11 ].

This review examines the application of deep learning (DL) in understanding breast cancer images. We start by pointing out the significance of imaging in nervous system science and its clinical advantages. The review is continued by discussing DL advancements in breast cancer diagnosis. The capabilities of such frameworks, their challenges and possible solutions, and related datasets are investigated. The primary contributions of this paper are:

• Recent articles (from 2018 to 2022) regarding the application of DL in breast cancer diagnosis are reviewed.
• Open datasets related to breast cancer diagnosis are introduced, and their web links are given.
• Publicly available source codes related to existing papers are listed with their web links.
• Current challenges and possible future direction are given regarding the application of DL in breast cancer diagnosis.

The rest of the paper is organized as follows: a brief introduction of digital pathology, breast cancer, and the potential of artificial intelligence (AI) to automate the diagnosis process is given in Section 2 . A set of datasets, existing literature, and challenges in breast cancer diagnosis using DL are given in Section 3 . Discussion is presented in Section 4 followed by the conclusion in Section 5 .

2. Digital Pathology and Deep Learning

Pathology is represented by a variety of terms, including “computerized pathology”, “AI”, and “computational pathology”. With the advancement of fluorescent slide scanners, entire glass slides can be virtualized and digitized [ 12 ]. The data from the slides can be saved in cloud storage, allowing pathologists to analyze the data with ease and the benefit of assistance from AI-based diagnosis tools [ 13 , 14 ]. To this end, researchers have already developed a variety of AI methods for medical diagnosis [ 15 ].

Breast cancer is the most widely recognized malignant growth in women, accounting for nearly half of cancer cases diagnosed in women [ 16 , 17 ]. HR-positive and lymph hub-negative infections also account for nearly half of all cases [ 18 , 19 , 20 ]. Following widespread clinical approval, multigene tests such as the Oncotype DX 21-gene test, PAM50, and Mamma Print are used to examine patients and guide ACTx in HR-positive and lymph node-negative breast cancer [ 21 , 22 ]. The clinical benefit of the 21-gene test is debatable in patients with HR-positive, lymph hub-negative, and early-stage breast cancer [ 23 , 24 ]. Furthermore, the fragility of RNA extracted from formalin-fixed paraffin-inserted (FFPE) tissue may jeopardize its precision and prevent proper interpretation of recurrence score (RS) results [ 24 ]. As a result, a simpler and more effective strategy for determining the risk of repetition based on super-durable tissue is required. Considering that the RS from the 21-gene test is not entirely determined by the expansion qualities bunch score (MKI67, STK15, BIRC5, CCNB1, and MYBL2) and that the mitotic count is linked to the RS7, a careful obsessive evaluation of mitosis and other cell-cell collaborations includes the RS7. Recently, the Lunit Extension has been demonstrated to predict mitosis accurately in every cell in bosom malignant growth [ 25 ], as well as recognized cancer cells and other cells in a microenvironment.

Breast carcinoma is the most common malignant growth in women worldwide, and it encompasses a wide range of diseases with varying histological, prognostic, and clinical outcomes [ 26 , 27 ]. Metastatic infections, such as liver and cellular breakdowns in the lungs, affect a majority of patients with malignant bosom growth [ 28 ]. A comprehensive genomic analysis of bosom disease patients identified key drivers of hereditary transformations responsible for therapeutic ramifications and outcome prediction [ 29 ].

3. Automated Breast Cancer Diagnosis

Inspired by the working mechanism of the human brain, artificial neural networks (ANNs) exploit multi-layer complex neuron structures to achieve high representation power [ 30 ]. Promising results of ANNs encouraged researchers to develop convolutional neural networks (CNNs) to handle high dimensional data such as images [ 31 , 32 ]. Thanks to automatic feature extraction using convolutional and max pooling layers, CNNs are able to learn challenging tasks [ 33 , 34 ].

3.1. Search Strategy

In this section, the search strategy for gathering existing papers related to breast cancer diagnosis is explained. To conduct our search, an AND/OR combination of multiple keywords was used: (breast cancer diagnosis OR malignant growth OR tumor) AND (deep learning OR machine learning). A total of 514 papers were gathered. Inclusion/exclusion of the gathered papers was performed based on authors’ voting. Papers with at least three votes were considered for inclusion in this survey. The number of selected papers categorized by their publishers were 10, 15, 28, and 19, corresponding to Elsevier, Springer, IEEE, and other publishers. These statistics correspond to the first blue row of Figure 1 . We repeated our search among the references of the selected papers. Among the selected papers, 9, 9, 16, and 13 belonged to Elsevier, Springer, IEEE, and other publishers, which have been added to the statistics in the first blue row of Figure 1 to yield the values in the second blue row of the same figure.

The statistics of the selected papers are categorized according to their publishers.

3.2. Breast Cancer Datasets

There are multiple publicly available datasets for breast cancer diagnosis. To aid cancer detection, some datasets contain viewpoint, malignant growth box, impediment, and other characteristics [ 35 , 36 ]. We undertook extensive research to identify notable breast cancer datasets, which are summarized in Table 1 .

Breast Cancer datasets and their links.

3.3. DL Application in Breast Cancer Diagnosis

AI has recently demonstrated promising results in terms of precision and accuracy for the automated diagnosis of diseases such as breast cancer [ 37 , 38 ]. Among AI methods, DL stands out for processing high-dimensional data such as medical images [ 39 , 40 ]. An extensive search has been conducted to gather articles related to breast cancer diagnosis. The majority of these articles were gathered from the Nature database, bosom malignant growth. Significant effort has been put into covering recently published articles, especially the ones with publicly available source codes. The remainder of this section is devoted to the overview of the investigated papers.

Wang et al. (the winning team in the CAMELYON16 challenge) created various models using 256 × 256-pixel patches from positive and negative areas of whole slide images of bosom sentinel lymph hubs [ 41 ]. Pathologists reported that having a profound learning framework as an assistant decreases the human error rate by 85% [ 42 ]. Other studies reported that estrogen receptor status (trauma centers) is a fundamental atomic marker used to diagnose and select treatment options [ 43 , 44 , 45 ].

During clinical administration, pathologists examine biopsied tissue for the designated receptor with immunohistochemistry (IHC) to detect cell surface antigens [ 46 , 47 ]. Due to the importance of tissue analysis, attempts have been made to automate it using DL. For example, two deep neural networks (DNNs) were attached end-to-end for local and global feature extraction from microscopy images [ 48 ]. The first network acts as an autoencoder for efficient dimensionality reduction, and the second network takes the job of classification. The steps of this approach are shown in Figure 2 .

The end-to-end attachment of two networks: 1. Patch-wise CNN, 2. Image-wise CNN.

Determining the factor with a high impact on cancer patients’ survival is vital for slowing down the cancer progression and increasing the life expectancy of the patients. To this end, Cho et al. [ 49 ] investigated the correlation between HE-stained tissue slides and adjuvant chemotherapy benefits for cancer patients. A CNN was trained on 1343 patients to identify histological parameters based on HE-stained whole slide images. The resulting method was called Lunit SCOPE, the steps of which are shown in Figure 3 .

Chemotherapy in hormone receptor-positive breast cancer patients.

Another examination approach is a mammogram, which is an X-ray picture of the breast. This approach is even useful for regular examinations of women with no signs of breast cancer. This is particularly important for early diagnosis and taking preventive actions to reduce the potential threat of breast cancer. To this end, Shen et al. [ 50 ] utilized DL to diagnose breast cancer based on mammograms. To reduce the cost of preparing a sufficient amount of training data, two sets of training data with different annotations were considered. A limited set of samples with lesion-level annotation was used in the first phase of training. In the second phase, only samples with image-level annotation were used. The cost of image-level annotation is much less than lesion-level annotation, which is appealing. The high-level steps of the aforementioned method are depicted in Figure 4 .

Whole image classification and prediction of cancer or normal.

Given that mammography is a reliable approach for breast cancer diagnosis, Petrini et al. [ 51 ] have utilized two mammography images (bilateral craniocaudal and mediolateral oblique views) to enhance the diagnosis performance. Their method is based on EfficientNet and has two major components, which are the patch classifier and the whole-image classifier. The patch classifier inspects small sub-images, and the whole classifier uses the patch classifier to scan the whole mammogram. The high-level schematic of this method is depicted in Figure 5 . As can be seen, the two mammograms are processed in parallel.

Diagrams of the single-view classifier for the “CV test” ( top ) and “OD test” ( bottom ).

In addition to mammography, the detection of small tumors helps with the early diagnosis of breast cancer. To this end, the STAN method [ 52 ] has been proposed, which utilizes multiple convolution operations with different kernel sizes to capture breast tumors of various sizes (including small ones). The architecture of STAN is illustrated in Figure 6 , in which convolutions with different sizes have been marked with different colors.

Small Tumor-Aware Network (STAN) to improve the performance of segmenting tumors with different sizes.

Researchers have observed that nuclear protein Ki-67 and tumor-infiltrating lymphocytes (TILs) are important factors for breast cancer diagnosis. Due to the lack of publicly available datasets for Ki-67 stained cell detection, Negahbani et al. [ 53 ] gathered such a dataset for public use. Additionally, a DNN named PathoNet was proposed which is a light backbone for cancer diagnosis. To facilitate experimenting with different DL models, a generic pipeline for cancerous cell detection was proposed that is compatible with a variety of DL models.

Although achieving state-of-the-art diagnosis performance is important, the ability to interpret the decision-making of DL models should not be overlooked. Being able to reason about the decision-making process is useful to gain better insight into the strengths and weaknesses of DL models. To this end, Patil et al. [ 54 ] took a multi-instance learning approach in a weakly supervised manner for the classification of breast cancer histology images. As shown in Figure 7 , each input image is partitioned into multiple smaller patches. Feeding these patches to the feature extractor module, attention scores are computed, which are used to compute bag-level features. The classification is performed based on the bag-level features.

Multi-instance learning architecture for classification of breast cancer histopathology images.

Graph neural networks have also been used to achieve interpretable results from DL models [ 55 ]. To this end, a set of quantitative metrics has been proposed to provide pathologists with understandable output. Four graph explainability methods have been used, which are based on graph pruning, gradient-based saliency, and layer-wise relevance propagation. The joint process of classification and explainability data preparation is shown in Figure 8 .

Proposed model based on graph breast cancer identification.

Despite the considerable potential of DL in the medical domain, medical experts do not fully trust DL. To gain the experts’ trust, the output of DL models must be human-readable (i.e., interpretable). Chauhan et al. [ 56 ] have used DL for the prediction of genomic biomarkers such as TP53 mutation, PIK3CA mutation, ER status, etc. The motivation is that classification of genomic biomarkers based on gene expression data is costly and may not be available or sometimes even not feasible. On the other hand, genomic biomarker prediction using DL is an affordable and accessible alternative that is helpful for planning effective treatments. The overall schema of this method is illustrated in Figure 9 .

Predict genomic biomarkers—TP53 mutation model.

It is also crucial to investigate the effect of using different CNN architectures and hardware processing platforms for breast cancer diagnosis. Such investigation has been undertaken for microscopic images of sentinel lymph tissue [ 15 , 57 , 58 ]. In particular, Bonnet [ 59 ] has conducted careful experiments to evaluate diagnostic performance using different CNN architectures and processing hardware platforms. Moving forward, Bonnet has investigated the effect of using transfer learning, hyperparameter tuning, and data augmentation on the diagnostic performance of DL models.

Considering that cancer is a chronic disease, monitoring the patient’s status during treatment is critical. Wang et al. [ 60 ] have proposed a TopoTxR pipeline for predicting the response to breast cancer treatment. To this end, 1D and 2D topological structures were extracted from breast MRI. Based on these 1/2D structures, new images were created in which voxels corresponding to the extracted structures were set to values in the breast MRI, and the rest were set to zero. The created images were fed to a simple CNN for pathological complete response prediction. The high-level steps of the TopoTxR method are depicted in Figure 10 . To facilitate the comparison of existing methods, some of them are summarized in Table 2 . Moreover, the set of articles that have accompanying public source codes are gathered in Table 3 .

Proposed TopoTxR Method.

Summary of reviewed articles.

Articles that have open-source codes.

3.4. DL Challenges

Despite achieving remarkable results, DL also has its drawbacks [ 69 , 70 ]. To reach acceptable performance, DL methods need a tremendous amount of training data which is hard to come by in the medical domain [ 71 , 72 ]. Preparing training data requires manual labeling which must be carried out by pathologists. This process is costly and requires a considerable amount of time. Moreover, accessing a sufficient number of pathologists may not always be possible [ 7 , 73 ]. Another critical limitation of DL methods is their deterministic nature [ 74 , 75 ]. A well-trained DL model performs well on samples similar to the ones observed during training but fails miserably upon encountering out-of-distribution (OOD) samples. Providing the wrong diagnosis is not acceptable in safety-critical applications such as medical diagnosis. Therefore, it is crucial to develop uncertainty-aware DL models which can estimate how confident they are about their predictions [ 76 , 77 ]. Uncertainty-aware DL has already been investigated in multiple studies [ 78 , 79 , 80 ], but the field is still an active area of research.

Despite the drawbacks mentioned above, DL has excellent potential for handling challenging tasks [ 81 , 82 ]. For example, in the Camelyon Amazing Test 2016, DL-based approaches were evaluated for disease diagnosis in hematoxylin and eosin (H&E)- stained whole slide imaging (WSI) [ 83 ]. Promising outcomes were achieved with a cancer location pace of 92.4%, where a pathologist could accomplish 73.2% responsiveness [ 10 ]. Through worldwide joint efforts, computational pathology aims to work on symptomatic exactness, better patient treatment, and treatment cost reduction. Developing better breast cancer diagnosis systems using DL is a crucial part of this objective.

In the last 10 to 15 years, many articles in light of DL have been published [ 84 , 85 ]. Despite significant progress in the field of breast cancer diagnosis, there is still room for improvement. Explainable AI [ 86 ] is a research topic that strives to shed light on the complex working mechanism of DL models. Considering that medical diagnosis is safety-critical, careful analysis of DL-based diagnosis systems is an important future aspect [ 87 , 88 ]. Such analysis demands a sufficient amount of annotated data, which is still limited. Therefore, preparing more labeled data is also important for future work [ 89 , 90 ].

4. Discussion

Early diagnosis and treatment of breast cancer heavily contribute to increasing life expectancy [ 91 ]. In developed countries, age-normalized breast cancer mortality fell by 40% between the 1980s and 2020 [ 92 ]. Breast cancer mortality has been reduced by 2 to 4 percent per year in nations that have taken effective treatment strategies [ 93 , 94 ]. Assuming that the breast cancer mortality rate is decreased by 2.5 percent per year, it is anticipated that 2.5 million more patients will stay alive from 2020 to 2040 [ 95 , 96 ].

As a worldwide issue, breast cancer took more than 600,000 lives in 2018. Screening mammography is very effective at reducing bosom disease mortality by 20–40%, and it is recommended by health organizations worldwide for early detection of malignant growth locations [ 97 , 98 ]. Information obtained from our provincial disease reconnaissance framework revealed the status of breast cancer growth endurance and mortality rate in northwestern Iran [ 99 ]. Generally, Iran has better breast cancer explicit endurance and a lower mortality rate compared to the country’s general breast cancer growth explicit endurance. However, breast cancer endurance is still lower than in developed nations [ 100 , 101 ].

Breast cancer was reported as the third most common malignant growth in the studies carried out in Iran [ 102 ]. The US and Western Europe have reported the highest breast cancer rate, while East Asia has reported the lowest [ 8 , 103 ]. Iran is one of the countries with a rising cancer rate and mortality rate. On the other hand, in agricultural nations, these rates are lower [ 30 ]. The aging population, variation to the Western way of life, no full-term pregnancy, late age at first pregnancy, lack of bosom healthcare services, hormonal pregnancy control, and being overweight have contributed to these patterns [ 104 , 105 , 106 ].

Over the last decade, early diagnosis and efficient treatment have increased the age-normalized life expectancy of patients in developed countries. However, patients in some low-income nations in Africa and Asia still suffer lower life expectancy [ 87 , 107 ]. The Harmony study indicates that the 5-year net endurance rate for bosom malignant growth has consistently increased to almost 80% in numerous nations [ 108 , 109 ]. Breast cancer disease explicit endurance paces of 81–86% have been reported for Britain, Belgium, Canada, the US, and Italy, while comparable figures are much lower in Malaysia (68%), India (60%), Mongolia (57%), and South Africa (53%) [ 108 ]. These significant differences might be due to the absence of oncology administrations and medicines, similar to the absence of early diagnosis and screening offices [ 110 ]. As indicated by a new Iranian review, the one-, three-, and five-year bosom malignant growth explicit endurance rates were 95.6%, 80.8%, and 69.5%, respectively [ 111 ]. Nevertheless, when compared with developed nations, endurance to bosom malignant growth is much lower in Iran, which is partly due to improper treatment modalities [ 112 , 113 , 114 , 115 , 116 ]. It has also been reported that growth size, lymph hub contribution, growth grade, financial status, and genetic inheritance are among the primary factors related to bosom disease explicit endurance [ 117 , 118 , 119 ]. Disease libraries give basic data to local area-wide anticipation endeavors.

Identifying the major risk factors contributing to breast cancer is crucial for diagnosing breast cancer and controlling its progress. Several studies have been devoted to risk factor identification. For example, Zhang et al. [ 120 ] have identified 17 immune genes that were considered prognostic biomarkers for breast cancer. Using these genes and AI, a survival prediction system for breast cancer patients was proposed. Predicting cancer risk as accurately as possible is highly desirable. To this end, Behravan et al. [ 121 ] utilized XGBoost [ 122 ] to develop an approach for determining the combination of interacting genetic variants and demographic risk factors leading to maximum accuracy in breast cancer risk prediction. Liu et al. [ 123 ] have also utilized the XGBoost method to identify risk factors contributing to breast cancer in menopausal women. Given the importance of risk factors contributing to breast cancer, Sharma et al. [ 124 ] have devoted a full survey on risk factors and assessment models for breast cancer and pointed out that patients at high risk must receive more frequent examinations.

Automated diagnostic tools not only increase the efficiency of the examination process but also reduce the workload of radiologists. To this end, a commercial AI diagnostic tool was used for breast cancer detection. Based on the AI tool output, the mammograms of patients were triaged in order to reduce the number of patients that undergo radiology [ 125 ]. It is possible to prepare models utilizing H&E stains as information and IHC explanations as info marks. This is suitable for multi-instance learning (MIL) [ 126 , 127 ]. Recently, MIL has been utilized to predict ML-driven histopathology [ 128 ].

ML approaches for medical diagnosis need to be interpretable, i.e., they must be able to specify the regions of interest in the image. Interpretability is fundamental to gaining medical experts’ trust in using automated diagnosis systems based on ML [ 129 , 130 ]. The field of interpretable AI is itself a major research area that is crucial to gaining a better understanding of black box ML models such as DNNs. Based on the nature of the ML model, available data, and interpretation strategy, interpretable AI methods have been categorized [ 131 ]. In future work, it is imperative to determine interpretable AI methods best suited for the medical diagnosis domain. The progress toward incorporating interpretability in AI models for medical applications has already started. For example, Karatza et al. [ 132 ] have proposed an ensemble of neural networks for breast cancer diagnosis and evaluated its interpretability using individual conditional expectation (ICE) [ 133 ] plots. Some other metrics to evaluate the interpretability of AI models are the global surrogate (GS) [ 134 , 135 ] method and the Shapley values (a method borrowed from game theory) [ 136 , 137 ].

5. Conclusions

In this review, we looked at the most recent research on breast cancer diagnosis using DL in image modalities. Various well-known DL methods such as CNN, RNN, GoogLeNet, ResNet, and ANN have been used in the literature for breast cancer diagnosis. In addition to reviewing existing DL-based diagnosis methods, the publicly available datasets and source code repositories were introduced as well. Inspection of the existing approaches reveals the significant progress toward automated diagnosis using DL. However, the reliability of these automated systems is yet to be improved before full deployment in real-world applications.

Over the years, the field of DL has made significant progress to the point that model representation power is rarely the limiting factor. However, without having a sufficient number of training samples, these powerful models will be of no use. Dealing with limited training data is an ongoing research field and can be tackled using different approaches. The most obvious way of addressing data shortage is gathering high-quality datasets that are publicly available. However, data collation is not always possible. Image composition is an alternative promising approach that can be used to create new samples by merging two images [ 138 ]. In this technique, several background and foreground images are combined in different ways to generate new training samples. Transfer learning is another strategy to deal with data scarcity. It is highly desirable to make transfer learning domain-aware [ 139 ]. Oftentimes, existing pre-trained models have been trained on general-purpose datasets such as ImageNet, which bears little resemblance to medical images. To address this issue, it is better to pre-train models on datasets that share common features with our target dataset.

While DL models are general-purpose learners, relying solely on image data is a short-sighted strategy. Investigating the possibility of performance improvement via fusing multiple sources of data [ 140 ] is worth investigating. A different but related approach is utilizing an ensemble of DL models for more robust decision making. The challenge is reducing the complexity of ensemble DL models in order to achieve better performance with manageable computational complexity. Knowledge distillation approaches [ 141 , 142 ] may be useful in making ensemble methods computationally efficient without losing much performance.

Funding Statement

This work was supported by the Science and Technology Ph.D. Research Startup Project under No. Grant SZIIT2022KJ001 and the funding of the Guangdong Provincial Research Platform and Project (2022KQNCX233).

Author Contributions

Conceptualization, M.S.I. and W.A.; methodology, R.A., S.H. and R.R.; software, M.S.I. and W.A.; validation, R.A., S.H. and R.R.; formal analysis, M.S.I. and W.A.; investigation, R.A., S.H. and R.R.; resources, M.S.I. and W.A.; data curation, R.A., S.H. and R.R.; writing—original draft preparation, M.S.I. and W.A.; writing—review and editing, R.A., S.H. and R.R.; visualization, M.S.I. and W.A.; supervision, R.A., S.H. and R.R.; project administration, M.S.I. and W.A.; funding acquisition, R.A., S.H. and R.R. All authors have read and agreed to the published version of the manuscript.

Institutional Review Board Statement

Informed consent statement, data availability statement, conflicts of interest.

The authors declare no conflict of interest.

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 05 June 2024

Clinical Studies

A nationwide study of breast reconstruction after mastectomy in patients with breast cancer receiving postmastectomy radiotherapy: comparison of complications according to radiotherapy fractionation and reconstruction procedures

• Hyejo Ryu 1 , 2 ,
• Kyung Hwan Shin 2 , 3 , 4 ,
• Ji Hyun Chang   ORCID: orcid.org/0000-0001-5921-5522 2 , 3 &
• Bum-Sup Jang   ORCID: orcid.org/0000-0002-7064-9855 2 , 3  

British Journal of Cancer ( 2024 ) Cite this article

Metrics details

• Breast cancer
• Radiotherapy
• Reconstruction

We examined the patterns of breast reconstruction postmastectomy in breast cancer patients undergoing postmastectomy radiotherapy (PMRT) and compared complications based on radiotherapy fractionation and reconstruction procedures.

Using National Health Insurance Service (NHIS) data (2015–2020), we analysed 4669 breast cancer patients with PMRT and reconstruction. Using propensity matching, cohorts for hypofractionated fractionation (HF) and conventional fractionation (CF) were created, adjusting for relevant factors and identifying grade ≥3 complications.

Of 4,669 patients, 30.6% underwent HF and 69.4% CF. The use of HF has increased from 19.4% in 2015 to 41.0% in 2020. Immediate autologous (32.9%) and delayed two-stage implant reconstruction (33.9%) were common. Complication rates for immediate ( N  = 1286) and delayed two-stage ( N  = 784) reconstruction were similar between HF and CF groups (5.1% vs. 5.4%, P  = 0.803, and 10.5% vs. 10.7%, P  = 0.856, respectively) with median follow-ups of 2.5 and 2.6 years. HF showed no increased risk of complications across reconstruction methods.

A nationwide cohort study revealed no significant difference in complication rates between the HF and CF groups, indicating HF for reconstructed breasts is comparable to CF. However, consultation regarding the fractionation for reconstructed breast cancer patients may still be necessary.

Similar content being viewed by others

Neoadjuvant radiochemotherapy is safe and feasible for breast conserving surgery or immediate reconstruction

Survival comparison between postoperative and preoperative radiotherapy for stage I–III non-inflammatory breast cancer

The optimization of postoperative radiotherapy in de novo stage IV breast cancer: evidence from real-world data to personalize treatment decisions

Introduction.

The escalating incidence of breast cancer has led to a corresponding rise in the number of breast cancer patients opting for breast reconstruction. This trend is particularly evident in South Korea, where breast reconstruction surgery following mastectomy gained coverage under the National Health Insurance Service (NHIS) in April 2015. Consequently, the rate of breast reconstruction cases in South Korea rose from 19.4% in 2015 to 53.4% in 2018 [ 1 ]. Similarly, the number of patients requiring postmastectomy radiotherapy (PMRT) is also expected to increase, given that PMRT is administered to one-third of breast cancer patients [ 2 ]. Despite the growing number of patients undergoing breast reconstruction and PMRT, the question of determining the optimal approach for patients receiving PMRT remains unsolved.

PMRT is associated with reconstruction-related complications and negatively impacts patients’ satisfaction. According to the Mastectomy Reconstruction Outcomes Consortium (MROC), PMRT significantly elevated the risk of complications by 2.6 times higher in patients with implant-based reconstructions compared to those who did not receive PMRT [ 3 ]. Likewise, irradiated autologous flaps exhibited a stronger association with fat necrosis and revision surgery compared to unirradiated flaps [ 4 ]. Patients with implant reconstruction and PMRT reported the lowest satisfaction levels [ 3 ]. These findings highlight the importance of finding strategies to minimise reconstruction-related complications.

Breast reconstruction is a multifaceted procedure that encompasses a variety of options, making it difficult to reach a consensus on the integration of reconstruction and PMRT. There are several approaches for breast reconstruction in terms of timing and materials. The timing of reconstruction can be classified as immediate, delayed, or a combination of both (delayed two-stage) [ 5 ]. In delayed two-stage reconstruction, known as delayed-immediate, a tissue expander is placed immediately with mastectomy, and it is exchanged for the implant or autologous tissues later [ 6 ]. Reconstruction materials can be either implants or autologous tissue such as fat or muscle, each with its unique advantages and drawback. While autologous flaps exhibit greater tolerance to irradiation compared to implants, not all patients are eligible for autologous reconstruction.

The advancements in radiation techniques have also added to the complexity of PMRT in reconstructed breasts. One of the major changes is the adoption of hypofractionation in breast cancer radiotherapy. By delivering a higher dose per fraction, HF can reduce treatment duration. Apart from convenience, HF has demonstrated comparable oncological outcomes to conventional fractions while exhibiting similar or even superior toxicity results [ 7 , 8 , 9 , 10 ]. However, these studies excluded patients with breast reconstruction. Consequently, the use of hypofractionation for reconstructed breasts remains controversial. For instance, the ESTRO guideline recommends adopting hypofractionation regardless of any oncoplastic surgery, while the ASTRO guideline does not yet endorse it [ 11 , 12 ].

Therefore, we conducted a nationwide study to examine the current practices in breast reconstruction with PMRT following the implementation of insurance reimbursement in 2015. In addition, we compared the complication rates associated with hypofractionation and conventional fractionated PMRT. Ultimately, this study aimed to provide comprehensive nationwide data on breast reconstruction approaches and evidence for the comparable safety of HF for patients undergoing breast reconstruction.

Materials and methods

Data sources and study population.

In South Korea, medical services in South Korea are covered by the NHIS, so it harbours large datasets of healthcare utilisation on a nationwide scale. It can provide demographic information, death information, and medical services utilisations at outpatient clinics as well as admissions. For research purposes, any researcher with ethical approval from the institutional review board can request the database. The personal information is deidentified, and analysis can be performed by using the International Statistical Classification of Diseases and 10th revision (ICD-10), and a procedure or operation code.

The study was approved by the Seoul National University Hospital’s Institutional Review Board (Number 2204-067-1315). The need for informed consent was waived due to the use of pseudonymized data. We requested a customised NHISS database of Korean female breast cancer patients who underwent mastectomy and postmastectomy radiation therapy (PMRT) between 2015 and 2020. The operational codes used for this study are listed in Supplementary Table  1 . The study period was between 2015 and 2021. This period was chosen to capture the impact of the reimbursement for breast reconstruction, which began in 2015. Among the 58,028 women with mastectomy and radiation therapy for breast cancer (ICD-10; C50) between 2015 and 2020, we initially excluded no history of reconstruction ( n  = 6020) (Supplementary Fig.  S1 ). Next, we excluded patients with multiple mastectomies ( n  = 925), time interval longer than 1 year between mastectomy and PMRT ( n  = 7950), and PMRT number less than 14 or greater than 35 ( n  = 38,464).

Finally, there were 4669 patients eligible for a pattern of care analysis.

Definitions

PMRT was administered following mastectomy surgery. Information on fraction size or number was unavailable in the database; therefore, the number of claim codes for radiation treatment, including chest wall and tumour bed boost irradiation, was considered to represent the fraction number. Only claim codes recorded up to three months from the initial PMRT date were counted. Using the survey result of the pattern of care study conducted by the Korean Radiation Oncology Group, we divided fractionation groups as follows [ 2 ]. Conventional fractionation (CF) was defined as 25–35 radiation treatments, assuming a total dose of at least 45-50 Gy in 1.8–2.0 Gy fractions. Conversely, hypofractionation (HF) was defined as 14 to 24 radiation treatments, assuming a total dose of 40–42.5 Gy in fractions greater than 2 Gy.

Breast reconstruction can be classified based on the reconstruction material and timing. Autologous breast reconstruction utilises tissue from the patient’s own body, such as latissimus dorsi (LD), transverse rectus abdominis musculocutaneous (TRAM), or deep inferior epigastric artery perforator (DIEP). Implant-based involves the placement of breast implants either a tissue expander (TE) or direct-to-implant (DTI). Regarding the timing of reconstruction, immediate reconstruction is performed on the same day as mastectomy or before the initiation of PMRT. Delayed reconstruction consisted of two types of reconstruction: one-stage and two-stage delayed reconstruction. One-stage delayed reconstruction involves reconstruction surgery after the completion of PMRT, while two-stage delayed reconstruction involves tissue expander insertion followed by PMRT and final definitive reconstruction.

The primary outcome of this study was the incidence of reconstruction-related complications requiring surgery following PMRT. Only surgeries performed by the Department of Plastic Surgery were considered complication events. We employed the operational codes for breast capsulectomy (breast capsulorrhaphy, capsulotomy, capsular flap), debridement, and skin graft. Capsulectomy performed on the day of final reconstruction was not considered a complication. Capsular contracture referred to capsulectomy performed exclusively in patients with implants. The capsular contracture was limited to patients requiring surgical intervention, because the specific procedure code for breast capsulectomy assigned by the national standard code was available. Wound complication was defined as an adverse event necessitating surgical debridement and skin graft. Patients with delayed two-stage complications were excluded if they lacked a final reconstruction history or complication history.

Statistical analysis

Basic descriptive statistics were used to examine the practice pattern trend in PMRT and breast reconstruction. The cohort was divided based on the timing of breast reconstruction (immediate vs. two-stage delayed reconstruction), and the toxicity outcomes between CF and HF were compared. Baseline characteristics between CF and HF were evaluated using t-tests and chi-square tests for continuous and categorical variables, respectively. To adjust the baseline characteristics between two fractionated regimens, a 1:1 greedy nearest propensity matching method was implemented in PSMATCH (SAS version 9.4) with a caliper of 0.2. Adjusted covariates included age, hypertension, diabetes, reconstruction material, IMRT, year of PMRT, and bolus. A standardised mean difference (SMD) of 0.2 was set as the cut-off value between the groups.

Crude complication rates between the two fractionation groups were compared using chi-squared tests. To account for the difference in the follow-up duration, a competing risk analysis for complications was performed, with death as the competing risk. Cox regression model was employed to identify variables associated with complications. Variables with a P value < 0.1 in univariate analysis were included in the multivariate analysis. The follow-up duration was defined as the time interval between the first date of PMRT and the date of the complication event, death, or the last visit. Categorical variables were represented as proportions with percentages. Continuous variables were expressed as medians with range. Data processing and statistical analyses were performed by Statistical Analysis System (SAS) version 9.4 (SAS Institute, Cary, NC, USA) and Stata version 15.0 (StataCorp, College Station, TX).

Practice patterns of postmastectomy radiotherapy and breast reconstruction

A significant increase in the utilisation of breast reconstruction and PMRT was observed, with the number of patients undergoing these procedures rising from 341 in 2015 to 962 in 2020. Among 4,669 breast cancer patients who received PMRT and reconstruction between 2015 and 2020, implants were employed in 59.2% of the cases (Fig.  1 a). Within the realm of autologous reconstruction, TRAM flaps were the most prevalent choice (38.5%), followed by DIEP (37.6%) and LD (23.9%) (Fig.  1 b). Immediate reconstruction was the most frequently performed timing strategy, accounting for 55.4% of patients. Delayed two-stage reconstruction was utilised in 36.0% of patients, followed by delayed one-stage reconstruction in 8.6% of patients (Fig.  1 c). When considering both reconstruction materials and timing, delayed two-stage implant reconstruction was the most common procedure, performed in 33.9% of the cohort. Immediate autologous reconstruction and immediate implant reconstruction followed with respective frequencies of 32.9% and 22.5% (Fig.  1d ). Regarding fractionation, 69.4% of the cohort received conventional fractionation (CF), while 30.6% underwent hypofractionation (HF). Notably, a gradual increase in the use of HF was observed, with the proportion of patients receiving HF rising from 19.4% (66 cases) in 2015 to 41.0% (394 cases) in 2020 (Fig.  1 e, f ).

a Rate of implant and autologous-based reconstructions. b Materials used for autologous reconstruction. c Types of breast reconstructions by timing. d Breast reconstruction by timing and material. e Rate of conventional fractionation and hypofractionated fractionation. f The yearly trend of fractionation for reconstructed breasts between 2015 and 2020. LD lattissimus dorsi, TRAM transverse rectus abdominis musculocutaneous, DIEP deep inferior epigastric artery perforator

Immediate breast reconstruction: baseline characteristics and complication incidence rate

A total of 2436 patients with immediate reconstruction were eligible for the complication analysis. Prior to propensity matching, there were 1793 patients in the CF group and 643 patients in the HF group. Table  1 summarises the baseline characteristics of the immediate reconstruction cohort before and after matching. In the unmatched cohort, HF was associated with recent year of PMRT, IMRT technique, and shorter follow-up periods. The proportion of implant use was marginally higher in the CF group. Significantly more patients in the CF group received bolus treatment. Following 1:1 matching, all variables except PMRT fraction number were well-balanced. The median PMRT fraction number of CF and HF patients was 28 and 17, respectively.

The matched cohort analysis revealed comparable follow-up durations between the CF and HF groups. Both groups had a median follow-up of 2.5 years, with a range of 0.3–5.9 years. During a median follow-up duration of 2.5 years, the complication rates were 5.4% in CF and 5.1% in HF ( P  = 0.803). The complication incidence was not significantly different between two groups (Fig.  2a ). Capsular contracture was the most common severe complication, occurring 7.1% in CF and 8.2% in HF ( P  = 0.627). The wound complications requiring debridement and skin graft were observed in 3.1% in CF and 2.5% in HF ( P  = 0.378). Figure  2b illustrates the cumulative incidence of complications, and the curves of the two fractionation groups did not differ from each other ( P  = 0.798). Similarly, there was no difference in complication incidence in the unmatched cohort as well (Supplementary Fig.  S2A ). In the matched cohort, implant-based immediate reconstruction was the only prognostic factor significantly associated with complications (hazard ratio (HR) 2.65, confidence interval (CI) 1.72–4.07, P  < 0.001, Table  2 ). However, HF, IMRT, and bolus were not identified as significant factors.

a Complication events in the matched immediate reconstruction cohort ( N  = 1286). b Cumulative incidence in the matched immediate reconstruction cohort ( N  = 1286). c Complication events in the matched two-stage delayed reconstruction cohort ( N  = 784). d Cumulative incidence in the matched two-stage delayed reconstruction cohort ( N  = 784).

Delayed two-stage breast reconstruction: baseline characteristics and complication incidence rate

In a retrospective analysis of 1347 patients undergoing delayed two-stage breast reconstruction, comprising 782 in the CF group and 565 in the HF group, the baseline characteristics of the unmatched and matched cohorts were compared (Table  3 ). Like the immediate breast reconstruction cohort, discrepancies were observed in the year of treatment, fraction number, intensity-modulated radiotherapy (IMRT) utilisation, bolus administration, and follow-up duration. The differences in the baseline characteristics were similar to the immediate cohort. Following propensity matching, the variables, except PMRT fraction number, were balanced between in the two groups. The median PMRT fraction number of CF and HF was 28 and 17, respectively. Unlike the immediate reconstruction cohort, implants were predominately used as the final reconstruction material. The median interval between PMRT and final reconstruction was 258 days (range 31–985 days).

The matched cohort had a median follow-up duration of 2.6 years (0.6–6.1 years), with the CF group at 2.8 years (0.9–6.1 years) and the HF group at 2.6 years (0.6–6.0 years). The overall incidence of complication did not differ significantly between the groups (CF: 10.5% and HF: 10.7%, P  = 0.856) (Fig.  2c ). Capsular contracture occurred in 7.9% and 5.1% in CF and HF, respectively ( P  = 0.111). Similarly, the wound complication rates did not differ significantly between the two groups (CF: 3.1% and HF: 5.3%, P  = 0.109). Furthermore, the cumulative complication incidence did not differ between the two groups ( P  = 0.766) (Fig.  2 d). This was also consistent in the unmatched group was observed as well (Supplementary Fig.  S2B ). Univariate and multivariate analyses revealed hypertension (HR 2.42, CI 1.39–3.5, P  = 0.002) and diabetes (HR 2.36, CI 1.36–4.01, P  = 0.002) to be significantly associated with an increased risk of complications (Table  4 ). Except for patients’ comorbidities, the factors related to radiation or reconstruction did not increase the risk of complications. Neither the use of bolus nor the time interval between PMRT and definitive surgery demonstrated prognostic significance.

This study represents the first population-based national cohort study to investigate the pattern of care and complications among patients with breast reconstruction and PMRT between 2015 and 2020. Despite the increasing number of breast reconstructions, uncertainties persist regarding the timing and materials employed in the context of PMRT. Moreover, with advancements in radiation technology, hypofractionation has emerged as a replacement for conventional fractionation in breast cancer treatment. However, despite several randomised prospective studies, the impact and safety of hypofractionation under breast reconstruction setting was not well studied. Here, we utilised the big data from the National Health Insurance Service and reported the current status of breast reconstruction and PMRT in the South Korean population and showed comparable complication rates regardless of fractional regimens.

Our nationwide cohort study revealed that immediate reconstruction (55.4%) was the most preferred approach, followed by delayed two-stage reconstruction (36.0%). Within immediate reconstruction, autologous tissues were preferentially selected over implants. This finding aligns with the concerns regarding the elevated complications risk associated with implants compared to autologous tissue in an immediate reconstruction setting. Despite these concerns, implants remained a population choice, probably due to the shorter surgery time, faster recovery, and no donor site morbidity. Delayed two-stage reconstruction with implants was also commonly performed in our cohort. This approach is endorsed by the NCCN, as the immediate implant placement carries an increased incidence of capsular contracture, malposition, and poor cosemesis [ 13 ]. However, delayed reconstruction using autologous tissue was rarely chosen compared to the immediate reconstruction setting.

We found comparable toxicity between CF and HF in the immediate reconstruction cohort [ 14 ]. Globally, a limited number of studies have investigated the use of HF in reconstructed breasts, with heterogeneity in fractionation regimen and complication rates. Another cohort study conducted in Brazil examined the safety of hypofractionated PMRT (2.65–2.67 Gy/fraction) in reconstructed breasts. Among 35 patients who underwent implant-based immediate reconstruction, capsular contracture developed in 11.4% [ 14 ]. In contrast, a U.S. Phase II trial reported an incidence of severe complications of 35% in 43 patients receiving a dose of 36.63 Gy in 11 fractions with a daily fraction size of 3.33 Gy [ 15 ].

Beyond compatibility between fractionation regimens, our study identified several associated risk factors for reconstruction-related complications. Implant usage emerged as the sole significant prognostic factor for complications. This aligns with existing knowledge regarding the increased susceptibility of implants to radiation-induced complications. Despite the elevated risk of adverse effects such as capsular contracture associated with implants, their popularity persists due to cost-effectiveness and broader eligibility compared to autologous tissues. Consequently, further advancements in implant-based reconstruction and radiation techniques are paramount to enhancing reconstruction outcomes. While bolus application has been shown to increase toxicity in reconstructed breasts, our study did not identify a significant association between bolus usage and complication risk. This discrepancy may arise from the application of different bolus definitions in our study and the prior literature. Bolus is more likely to induce skin-related toxicity, whereas our study focused primarily on complications requiring surgical interventions [ 16 ]. However, de Sousa et al. reported an increased risk of infection (HR 10.3, CI 1.7–61.8), and reconstruction failure (HR 13.89, CI 2.24–85.98) in patients undergoing two-stage reconstructions when bolus was applied daily [ 17 ]. In contrast, alternate-day bolus usage was not associated with complication risk. Therefore, it is still important that the decision to use bolus for PMRT should be individualised considering the benefits and the risks.

A recent prospective randomised trial, the Radiation Fractionation on Patient Outcomes After Breast REConstruction (FABREC) study, found no significant differences in oncologic outcomes or chest wall toxicity between conventional fractionation and hypofractionation in 400 patients with immediate implant-based reconstructions [ 18 ]. The FABREC trial also reported improved quality of life in patients over 45 years old, along with reduced treatment breaks and financial toxicity in the HF group. Another pivotal study, RT CHARM (ALLIANCE A221505), is currently underway and includes both immediate and delayed reconstruction. Its results are eagerly anticipated, as they will provide valuable data on the safety of hypofractionation in the reconstruction setting.

Addressing the role of acellular dermal matrix (ADM) in immediate implant-based breast reconstruction is vital due to its widespread use and potential impact on complications. ADM is a biomaterial processed to remove cellular components while preserving extracellular matrix structure. Until now, the effect of ADM on patients undergoing PMRT is not well defined, but a few retrospective studies suggested a protective role in irradiated patients [ 19 , 20 , 21 ]. However, our study could not directly identify its actual usage because it has not been reimbursed by the government. A multi-institutional data from the South Korea Radiation Oncology Group indicated its prevalence, with over 50% utilisation in breast reconstruction and PMRT between 2015 and 2016 [ 22 ]. Considering the contemporary reliance on ADM in breast reconstruction practices, it may be reasonable to assume its significant incorporation in our study population, especially since ADM is routinely integrated into implant-based reconstruction protocols at our institution.

In addition to ADM usage, it is also important to understand the dosimetric planning and target delineation in our population. While the specific planning protocols may vary among hospitals in South Korea, it seems to follow the general principle [ 23 ]. For the hypofractionation scheme, at least 95% planning target volume was required to be covered by 95% of the prescribed dose, and the maximum point dose (D max) was limited to below 105–107%. Organ-at-risk constraints ensured that the volume of the ipsilateral lung receiving 5 Gy (V5) and 20 Gy (V20) did not surpass 45% and 20%, respectively. The mean dose to the heart was maintained be low 3 Gy and 5 Gy for right-sided tumours and left-sided tumours, respectively. The most commonly utilised RT techniques were forward IMRT (field-in-field) followed by VMAT and 3D conformal, according to a multi-institutional retrospective study conducted in South Korea [ 22 ]. In terms of target delineation, it seems that there is no specific preference between RTOG and ESTRO guidelines among radiation oncologists in South Korea [ 23 ]. Also, some institutions adopted new ESTRO-ACROP target delineation guideline which allows excluding implants from the clinical target volume [ 24 , 25 ]. As there is no information on dosimetry planning and target delineations, it will be critical to interpret our results with caution.

Our study has several limitations. In our study, we excluded patients who received fewer than 14 or more than 35 fractions of radiotherapy, which could have arisen from various causes such as multiple treatment courses, treatment for metastatic lesions, or unconventional fractionation regimens. Furthermore, there may have been discrepancies between the actual number of fractions delivered and the number billed due to variations in billing practices and treatment principles across institutions. While it is challenging to derive precise radiation fractionation details from such a large-scale dataset, we believe existence of a significant difference in radiation fractions between the HF and CF groups presented, which is supported by several factors: First, the trend of increasing HF adoption in Korea since 2015 aligns with the observed pattern in our study [ 26 ]. Second, a separate analysis by Kim et al. using individual patient ( N  = 393) revealed comparable major breast complication rates (12.0% vs. 12.3%) following immediate reconstruction for both HF and CF groups [ 27 ]. While we recognise the inherent limitations of the nationwide database [ 28 ], we believe our study serves as a valuable step towards establishing a more robust and verifiable method for radiation fractionation assessment within national databases. Accurately filtering out such complexities from large datasets proved exceedingly challenging, necessitating an exclusion approach to maintain cohort homogeneity. Although this resulted in a reduced sample size, the enhanced treatment homogeneity within the cohort enabled us to draw more meaningful conclusions from our analysis. The radiation field or site could not be identified in the national database. Our definition of complications was limited to major events requiring capsulectomy, wound debridement, or skin graft by plastic surgeons. Other complications requiring only medical treatment were not included. Furthermore, the relatively short follow-up duration in some patients may have resulted in the failure to capture adverse events. Therefore, it is necessary to approach the interpretation of our findings with caution.

This nationwide study, the first to examine trends and complications in breast cancer patients undergoing both reconstruction and PMRT, revealed a moderate increase in the adoption of HF. Importantly, the major complication rates remained comparable between HF and CF, irrespective of the timing of reconstruction. Nevertheless, ongoing prospective trials on fractionation hold promise for further optimising PMRT strategies in this setting.

Data availability

Any researcher with an approved IRB can request a customised database to the National Health Insurance Data Sharing Service ( https://nhiss.nhis.or.kr/ ). Upon approval, all raw data were only accessible from “Data analysis room” located within the National Health Insurance Service (NHIS-2022-1-675).

Song WJ, Kang SG, Kim EK, Song SY, Lee JS, Lee JH, et al. Current status of and trends in post-mastectomy breast reconstruction in Korea. Arch Plast Surg. 2020;47:118–25.

Article   PubMed   PubMed Central   Google Scholar  

Yang G, Chang JS, Shin KH, Kim JH, Park W, Kim H, et al. Post-mastectomy radiation therapy in breast reconstruction: a patterns of care study of the Korean Radiation Oncology Group. Radiat Oncol J. 2020;38:236–43.

Jagsi R, Momoh AO, Qi J, Hamill JB, Billig J, Kim HM, et al. Impact of radiotherapy on complications and patient-reported outcomes after breast reconstruction. JNCI: J Natl Cancer Inst. 2018;110:157–65.

Article   PubMed   Google Scholar  

Liew B, Southall C, Kanapathy M, Nikkhah D. Does post-mastectomy radiation therapy worsen outcomes in immediate autologous breast flap reconstruction? A systematic review and meta-analysis. J Plast Reconstructive Aesthetic Surg. 2021;74:3260–80.

Article   Google Scholar  

Ho AY, Hu ZI, Mehrara BJ, Wilkins EG. Radiotherapy in the setting of breast reconstruction: types, techniques, and timing. Lancet Oncol. 2017;18:e742–e753.

Kronowitz SJ, Hunt KK, Kuerer HM, Babiera G, McNeese MD, Buchholz TA, et al. Delayed-immediate breast reconstruction. Plast Reconstr Surg. 2004;113:1617–28.

Haviland JS, Owen JR, Dewar JA, Agrawal RK, Barrett J, Barrett-Lee PJ, et al. The UK Standardisation of Breast Radiotherapy (START) trials of radiotherapy hypofractionation for treatment of early breast cancer: 10-year follow-up results of two randomised controlled trials. Lancet Oncol. 2013;14:1086–94.

Group TST. The UK standardisation of breast radiotherapy (START) Trial A of radiotherapy hypofractionation for treatment of early breast cancer: a randomised trial. Lancet Oncol. 2008;9:331.

Whelan TJ, Pignol J-P, Levine MN, Julian JA, MacKenzie R, Parpia S, et al. Long-term results of hypofractionated radiation therapy for breast cancer. New Engl J Med. 2010;362:513–20.

Article   CAS   PubMed   Google Scholar  

Wang SL, Fang H, Song YW, Wang WH, Hu C, Liu YP, et al. Hypofractionated versus conventional fractionated postmastectomy radiotherapy for patients with high-risk breast cancer: a randomised, non-inferiority, open-label, phase 3 trial. Lancet Oncol. 2019;20:352–60.

Smith BD, Bellon JR, Blitzblau R, Freedman G, Haffty B, Hahn C, et al. Radiation therapy for the whole breast: executive summary of an American Society for Radiation Oncology (ASTRO) evidence-based guideline. Pr Radiat Oncol. 2018;8:145–52.

Meattini I, Becherini C, Boersma L, Kaidar-Person O, Marta GN, Montero A, et al. European Society for Radiotherapy and Oncology Advisory Committee in Radiation Oncology Practice consensus recommendations on patient selection and dose and fractionation for external beam radiotherapy in early breast cancer. Lancet Oncol. 2022;23:e21–31.

Gradishar WJ, Lurie RH, Moran MS, Abraham J, Abramson V, Aft R, et al. NCCN Guidelines Version 3.2023 Breast Cancer. 2023. https://www.nccn.org .

de Siqueira GSM, Hanna SA, de Moura LF, Miranda FA, Carvalho H de A, et al. Moderately hypofractionated radiation therapy for breast cancer: a Brazilian cohort study. The Lancet Regional Health - Americas 2022;14. https://doi.org/10.1016/j.lana.2022.100323 .

Poppe MM, Yehia ZA, Baker C, Goyal S, Toppmeyer D, Kirstein L, et al. 5-Year update of a multi-institution, prospective phase 2 hypofractionated postmastectomy radiation therapy trial. Int J Radiat Oncol Biol Phys. 2020;107:694–700.

Dahn HM, Boersma LJ, de Ruysscher D, Meattini I, Offersen BV, Pignol JP, et al. The use of bolus in postmastectomy radiation therapy for breast cancer: a systematic review. Crit Rev Oncol Hematol. 2021;163:103391.

de Sousa CFPM, Neto ES, Chen MJ, Silva MLG, Abrahão CH, Ramos H, et al. Postmastectomy radiation therapy bolus associated complications in patients who underwent 2-stage breast reconstruction. Adv Radiat Oncol. 2022;7. https://doi.org/10.1016/j.adro.2022.101010 .

Wong JS, Uno H, Tramontano A, Pellegrini C, Bellon JR, Cheney MD, et al. Patient-reported and toxicity results from the FABREC study: a multicenter randomized trial of hypofractionated vs. conventionally-fractionated postmastectomy radiation therapy after implant-based reconstruction. Int J Radiat Oncol*Biol*Phys. 2023;117:e3–4.

Chung AM, Stein MJ, Ghumman A, Zhang J. The effect of post mastectomy radiation therapy on breast reconstruction with and without acellular dermal matrix: a systematic review and meta-analysis protocol. Syst Rev. 2019;8:1–4.

Article   CAS   Google Scholar  

Craig ES, Clemens MW, Koshy JC, Wren J, Hong Z, Butler CE, et al. Outcomes of acellular dermal matrix for immediate tissue expander reconstruction with radiotherapy: a retrospective cohort study. Aesthet Surg J. 2019;39:279–88.

Polotto S, Pedrazzi G, Bergamini M, D’Abbiero N, Cattelani L. ADM-assisted direct-to-implant prepectoral breast reconstruction in postmastectomy radiation therapy setting: long-term results. Clin Breast Cancer. 2023;23:704–11.

Chung SY, Chang JS, Shin KH, Kim JH, Park W, Kim H, et al. Impact of radiation dose on complications among women with breast cancer who underwent breast reconstruction and post-mastectomy radiotherapy: A multi-institutional validation study. Breast. 2021;56:7–13.

Chang JS, Song SY, Oh JH, Lew DH, Roh TS, Kim SY, et al. Influence of radiation dose to reconstructed breast following mastectomy on complication in breast cancer patients undergoing two-stage prosthetic breast reconstruction. Front Oncol. 2019;9. https://doi.org/10.3389/fonc.2019.00243 .

Kaidar-Person O, Vrou Offersen B, Hol S, Arenas M, Aristei C, Bourgier C, et al. ESTRO consensus guideline for target volume delineation in the setting of postmastectomy radiation therapy after implant-based immediate reconstruction for early stage breast cancer. Radiother Oncol. 2019;137:159–66.

Park JBin, Jang B-S, Chang JH, Kim JH, Choi CH, Hong KY, et al. The impact of the new ESTRO-ACROP target volume delineation guidelines for postmastectomy radiotherapy after implant-based breast reconstruction on breast complications. Front Oncol. 2024;14:1373434.

Park HJ, Kim K, Kim YB, Chang JS, Shin KH, Division for Breast Cancer KROG. Patterns and longitudinal changes in the practice of breast cancer radiotherapy in Korea: Korean Radiation Oncology Group 22-01. J Breast Cancer. 2022;26:15.

Google Scholar  

Kim DY, Park E, Heo CY, Jin US, Kim EK, Han W, et al. Influence of hypofractionated versus conventional fractionated postmastectomy radiation therapy in breast cancer patients with reconstruction. Int J Radiat Oncol Biol Phys. 2022;112:445–56.

Kyoung DS, Kim HS. Understanding and Utilizing Claim Data from the Korean National Health Insurance Service (NHIS) and Health Insurance Review & Assessment (HIRA) Database for Research. J Lipid Atheroscler. 2022;11:103–10.

Download references

Acknowledgements

This study used NHIS—National Health Information Database (NHIS-2022-1-675) made by National Health Insurance Service (NHIS). The author(s) declare no conflict of interest with NHIS.

This work was supported by grant no. 04-2023-2220 from the SNUH Research Fund, and the National R&D Program for Cancer Control through the National Cancer Center funded by the Ministry of Health & Welfare, Republic of Korea (HA22C0044). Open Access funding enabled and organized by Seoul National University.

Author information

Authors and affiliations.

Department of Radiation Oncology, Chung-Ang University Gwangmyeong Hospital, Gwangmyeong, Korea

Department of Radiation Oncology, College of Medicine, Seoul National University, Seoul, Korea

Hyejo Ryu, Kyung Hwan Shin, Ji Hyun Chang & Bum-Sup Jang

Department of Radiation Oncology, Seoul National University Hospital, Seoul, Korea

Kyung Hwan Shin, Ji Hyun Chang & Bum-Sup Jang

Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, South Korea

Kyung Hwan Shin

You can also search for this author in PubMed   Google Scholar

Contributions

Study concept and design: BSJ. Acquisition of the data: HR and BSJ. Analysis and interpretation of data: HR and BSJ. Drafting of the manuscript: HR and BSJ. Statistical analysis: HR and BSJ. Manuscript review and approval: KHS, JHC and BSJ. Obtained funding: KHS, JHC and BSJ. Study supervision: KHS, JHC and BSJ. All authors read and approved the submitted version of the manuscript.

Corresponding author

Correspondence to Bum-Sup Jang .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Ethics approval and consent to participate

The study was performed in accordance with the Declaration of Helsinki. This study was approved by the Institutional Review Board of the Seoul National University Hospital (IRB Number 2204-067-1315). The need for informed consent was waived because the data was anonymized.

Consent for publication

Not applicable.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementray information, rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Ryu, H., Shin, K.H., Chang, J.H. et al. A nationwide study of breast reconstruction after mastectomy in patients with breast cancer receiving postmastectomy radiotherapy: comparison of complications according to radiotherapy fractionation and reconstruction procedures. Br J Cancer (2024). https://doi.org/10.1038/s41416-024-02741-4

Download citation

Received : 15 November 2023

Revised : 23 May 2024

Accepted : 28 May 2024

Published : 05 June 2024

DOI : https://doi.org/10.1038/s41416-024-02741-4

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Advertisement

Breast Cancer Prediction: A Comparative Study Using Machine Learning Techniques

• Original Research
• Published: 01 September 2020
• Volume 1 , article number  290 , ( 2020 )

Cite this article

• Md. Milon Islam   ORCID: orcid.org/0000-0002-4535-5978 1 ,
• Md. Rezwanul Haque 1 ,
• Hasib Iqbal 1 ,
• Md. Munirul Hasan 2 ,
• Mahmudul Hasan   ORCID: orcid.org/0000-0002-4386-0356 3 &
• Muhammad Nomani Kabir 2  

11k Accesses

168 Citations

Explore all metrics

Early detection of disease has become a crucial problem due to rapid population growth in medical research in recent times. With the rapid population growth, the risk of death incurred by breast cancer is rising exponentially. Breast cancer is the second most severe cancer among all of the cancers already unveiled. An automatic disease detection system aids medical staffs in disease diagnosis and offers reliable, effective, and rapid response as well as decreases the risk of death. In this paper, we compare five supervised machine learning techniques named support vector machine (SVM), K-nearest neighbors, random forests, artificial neural networks (ANNs) and logistic regression. The Wisconsin Breast Cancer dataset is obtained from a prominent machine learning database named UCI machine learning database. The performance of the study is measured with respect to accuracy, sensitivity, specificity, precision, negative predictive value, false-negative rate, false-positive rate, F1 score, and Matthews Correlation Coefficient. Additionally, these techniques were appraised on precision–recall area under curve and receiver operating characteristic curve. The results reveal that the ANNs obtained the highest accuracy, precision, and F1 score of 98.57%, 97.82%, and 0.9890, respectively, whereas 97.14%, 95.65%, and 0.9777 accuracy, precision, and F1 score are obtained by SVM, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Similar content being viewed by others

Machine Learning Algorithms for Breast Cancer Detection and Prediction

Selecting Best Machine Learning Techniques for Breast Cancer Prediction and Diagnosis

Machine Learning Classifiers Performance Comparison for Breast Cancer Detection

Park SH, Han K. Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction. Radiol Soc N Am. 2018;286(3):800–9.

Google Scholar  

Breast Cancer: Statistics, Approved by the Cancer.Net Editorial Board, 04/2017. [Online]. Available: http://www.cancer.net/cancer-types/breast-cancer/statistics . Accessed 26 Aug 2018.

Mori M, Akashi-Tanaka S, Suzuki S, Daniels MI, Watanabe C, Hirose M, Nakamura S. Diagnostic accuracy of contrast-enhanced spectral mammography in comparison to conventional full-field digital mammography in a population of women with dense breasts. Springer. 2016;24(1):104–10.

Kurihara H, Shimizu C, Miyakita Y, Yoshida M, Hamada A, Kanayama Y, Tamura K. Molecular imaging using PET for breast cancer. Springer. 2015;23(1):24–32.

Azar AT, El-Said SA. Probabilistic neural network for breast cancer classification. Neural Comput Appl. 2013;23(6):1737–51.

Article   Google Scholar  

Nagashima T, Suzuki M, Yagata H, Hashimoto H, Shishikura T, Imanaka N, Miyazaki M. Dynamic-enhanced MRI predicts metastatic potential of invasive ductal breast cancer. Springer. 2002;9(3):226–30.

Park CS, Kim SH, Jung NY, Choi JJ, Kang BJ, Jung HS. Interobserver variability of ultrasound elastography and the ultrasound BI-RADS lexicon of breast lesions. Springer. 2013;22(2):153–60.

Ayon SI, Islam MM, Hossain MR. Coronary artery heart disease prediction: a comparative study of computational intelligence techniques. IETE J Res. 2020;. https://doi.org/10.1080/03772063.2020.1713916 .

Muhammad LJ, Islam MM, Usman SS, Ayon SI. Predictive data mining models for novel coronavirus (COVID-19) infected patients’ recovery. SN Comput Sci. 2020;1(4):206.

Islam MM, Iqbal H, Haque MR, Hasan MK. Prediction of breast cancer using support vector machine and K-Nearest neighbors. In: Proc. IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Dhaka, 2017, pp. 226–229.

Haque MR, Islam MM, Iqbal H, Reza MS, Hasan MK. Performance evaluation of random forests and artificial neural networks for the classification of liver disorder. In: Proc. International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), Rajshahi, 2018, pp. 1–5.

Ayon SI, Islam MM. Diabetes prediction: a deep learning approach. Int J Inf Eng Electron Bus (IJIEEB). 2019;11(2):21–7.

Islam MZ, Islam MM, Asraf A. A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images, 2020. pp. 1–20.

Hasan MK, Islam MM, Hashem MMA. Mathematical model development to detect breast cancer using multigene genetic programming. In: 2016 5th International Conference on Informatics, Electronics and Vision (ICIEV), pp. 574–579, 2016.

Sakri SB, Rashid NBA, Zain ZM. Particle swarm optimization feature selection for breast cancer recurrence prediction. IEEE Access. 2018;6:29637–47.

Juneja K, Rana C. An improved weighted decision tree approach for breast cancer prediction. In: International Journal of Information Technology, 2018.

Yue W, et al. Machine learning with applications in breast cancer diagnosis and prognosis. Designs. 2018;2(2):13.

Banu AB, Subramanian PT. Comparison of Bayes classifiers for breast cancer classification. Asian Pac J Cancer Prev (APJCP). 2018;19(10):2917–20.

Chaurasia V, Pal S, Tiwari B. Prediction of benign and malignant breast cancer using data mining techniques. J Algorithms Comput Technol. 2018;12(2):119–26.

Azar AT, El-Metwally SM. Decision tree classifiers for automated medical diagnosis. Neural Comput Appl. 2012;23(7–8):2387–403.

Senapati MR, Mohanty AK, Dash S, Dash PK. Local linear wavelet neural network for breast cancer recognition. Neural Comput Appl. 2013;22(1):125–31.

Senapati MR, Panda G, Dash PK. Hybrid approach using KPSO and RLS for RBFNN design for breast cancer detection. Neural Comput Appl. 2014;24(3–4):745–53.

Hasan MK, Islam MM, Hashem MMA (2016) Mathematical model development to detect breast cancer using multigene genetic programming. In: Proc. 5th International Conference on Informatics, Electronics and Vision (ICIEV), Dhaka, 2016, pp. 574–579.

Azar AT, El-Said SA. Performance analysis of support vector machines classifiers in breast cancer mammography recognition. Neural Comput Appl. 2013;24(5):1163–77.

Ferreira P, Dutra I, Salvini R, Burnside E. Interpretable models to predict Breast Cancer. In: Proc. IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Shenzhen, 2016, pp. 1507–1511.

Jhajharia S, Verma S, Kumar R. A cross-platform evaluation of various decision tree algorithms for prognostic analysis of breast cancer data. In: Proc. International Conference on Inventive Computation Technologies (ICICT), Coimbatore, 2016, pp. 1–7.

Islam MM, Rahaman A, Islam MR. Development of smart healthcare monitoring system in IoT environment. SN Comput Sci. 2020;1(3):185.

Rahaman A, Islam M, Islam M, Sadi M, Nooruddin S. Developing IoT based smart health monitoring systems: a review. Rev d’Intell Artif. 2019;33(6):435–40.

Breast Cancer Wisconsin (Original) Data Set, [Online]. https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data . Accessed 25 Aug 2018.

James G, Witten D, Hastie T, Tibshirani R. An introduction to statistical learning. 1st ed. New York: Springer; 2013.

Book   MATH   Google Scholar  

Guido S, Mller AC. Introduction to machine learning with python. Sebastopol: O’Reilly Media Inc.; 2016.

Dwivedi AK. Performance evaluation of different machine learning techniques for prediction of heart disease. Neural Comput Appl. 2016;29(10):685–93.

Ratner B. Statistical and machine-learning data mining: techniques for better predictive modeling and analysis of big data. Oxford: Chapman and Hall/CRC; 2017.

MATH   Google Scholar  

Dong L, Wesseloo J, Potvin Y, Li X. Discrimination of mine seismic events and blasts using the fisher classifier, naive bayesian classifier and logistic regression. Rock Mech Rock Eng. 2015;49(1):183–211.

Hosmer DW Jr, Lemeshow S. Applied logistic regression. New York: Wiley; 2004.

Schumacher M, Roner R, Vach W. Neural networks and logistic regression: part I. Comput Stat Data Anal. 1996;21(6):661–82.

Article   MATH   Google Scholar  

Vach W, Roner R, Schumacher M. Neural networks and logistic regression: part II. Comput Stat Data Anal. 1996;21(6):683–701.

Hajmeer M, Basheer I. Comparison of logistic regression and neural network-based classifiers for bacterial growth. Food Microbiol. 2003;20(1):43–55.

Xu Y, Zhu Q, Wang J. Breast cancer diagnosis based on a kernel orthogonal transform. Neural Comput Appl. 2012;21(8):1865–70.

Latchoumi TP, Parthiban L. Abnormality detection using weighed particle swarm optimization and smooth support vector machine. Biomed Res. 2017;28:4749–51.

Kumar UK, Nikhil MBS, Sumangali K. Prediction of breast cancer using voting classifier technique. In: Proc. IEEE International Conference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials (ICSTM), Chennai, 2017, pp. 108–114.

Download references

Acknowledgements

This research was partially supported by Universiti Malaysia Pahang (UMP) through UMP Flagship Grant (RDU192206).

Author information

Authors and affiliations.

Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, 9203, Bangladesh

Md. Milon Islam, Md. Rezwanul Haque & Hasib Iqbal

Faculty of Computing, Universiti Malaysia Pahang, 26300, Gambang, Kuantan, Malaysia

Md. Munirul Hasan & Muhammad Nomani Kabir

Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794-2424, USA

Mahmudul Hasan

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Md. Milon Islam .

Ethics declarations

Conflict of interest.

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the topical collection “Advances in Computational Approaches for Artificial Intelligence, Image Processing, IoT and Cloud Applications” guest edited by Bhanu Prakash K N and M. Shivakumar.

Rights and permissions

Reprints and permissions

About this article

Islam, M.M., Haque, M.R., Iqbal, H. et al. Breast Cancer Prediction: A Comparative Study Using Machine Learning Techniques. SN COMPUT. SCI. 1 , 290 (2020). https://doi.org/10.1007/s42979-020-00305-w

Download citation

Received : 11 August 2020

Accepted : 18 August 2020

Published : 01 September 2020

DOI : https://doi.org/10.1007/s42979-020-00305-w

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Breast cancer prediction
• Cancer dataset
• Machine learning
• Support vector machine
• Random forests
• Artificial neural networks
• K-nearest neighbors
• Logistic regression
• Find a journal
• Publish with us
• Track your research

Europe PMC requires Javascript to function effectively.

Either your web browser doesn't support Javascript or it is currently turned off. In the latter case, please turn on Javascript support in your web browser and reload this page.

Search life-sciences literature (44,166,401 articles, preprints and more)

• Available from publisher site using DOI. A subscription may be required. Full text

Association of depressive symptoms and sleep disturbances with survival among US adult cancer survivors.

Author information, affiliations.

BMC Medicine , 05 Jun 2024 , 22(1): 225 https://doi.org/10.1186/s12916-024-03451-7   PMID: 38835034 

Abstract 

Conclusions, full text links .

Read article at publisher's site: https://doi.org/10.1186/s12916-024-03451-7

References 

Articles referenced by this article (40)

Cancer statistics, 2023.

Siegel RL , Miller KD , Wagle NS , Jemal A

CA Cancer J Clin, (1):17-48 2023

MED: 36633525

Trends in the prevalence and treatment of comorbid depression among US adults with and without cancer, 2005-2020.

Yan G , Zhang Q , Yan Y , Zhang Y , Li Y , Liu M , Tian W

J Affect Disord, 743-750 2023

MED: 37598717

Insomnia in the context of cancer: a review of a neglected problem.

Savard J , Morin CM

J Clin Oncol, (3):895-908 2001

MED: 11157043

Depression in young people.

Thapar A , Eyre O , Patel V , Brent D

Lancet, (10352):617-631 2022

MED: 35940184

Healthcare use and costs in adult cancer patients with anxiety and depression.

Mausbach BT , Decastro G , Schwab RB , Tiamson-Kassab M , Irwin SA

Depress Anxiety, (9):908-915 2020

MED: 32485033

Suicide in Patients With Cancer: Identifying the Risk Factors.

McFarland DC , Walsh L , Napolitano S , Morita J , Jaiswal R

Oncology (Williston Park), (6):221-226 2019

MED: 31219606

Excess mortality in depression: a meta-analysis of community studies.

Cuijpers P , Smit F

J Affect Disord, (3):227-236 2002

MED: 12450639

Depression in sleep disturbance: A review on a bidirectional relationship, mechanisms and treatment.

Fang H , Tu S , Sheng J , Shao A

J Cell Mol Med, (4):2324-2332 2019

MED: 30734486

Pre-treatment symptom cluster in breast cancer patients is associated with worse sleep, fatigue and depression during chemotherapy.

Liu L , Fiorentino L , Natarajan L , Parker BA , Mills PJ , Sadler GR , Dimsdale JE , Rissling M , He F , Ancoli-Israel S

Psychooncology, (2):187-194 2009

MED: 18677716

New NCCN guidelines for survivorship care.

Ligibel JA , Denlinger CS

J Natl Compr Canc Netw, (5 Suppl):640-644 2013

MED: 23704233

Europe PMC is part of the ELIXIR infrastructure

Breast Cancer Research

Breast Cancer Risk Factors

Breast Cancer Research  is presenting our Retrospective Collection on "Breast Cancer Risk Factors." Celebrating 'Breast Cancer Awareness Month (1 October- 31 October)', with this Collection, we aim to gain valuable insights into the multifaceted aspects of breast cancer risk to promote awareness, prevention, and early detection.

NEW CROSS-JOURNAL COLLECTIONS Find out more by clicking the links below:

Artif icial Intelligence in Breast Imaging PDGFB in Br east Cancer Initiation,Progression, and Metastasis

Aims and scope

• Most accessed

NSUN2/YBX1 promotes the progression of breast cancer by enhancing HGH1 mRNA stability through m 5 C methylation

Authors: Xuran Zhang, Ke An, Xin Ge, Yuanyuan Sun, Jingyao Wei, Weihong Ren, Han Wang, Yueqin Wang, Yue Du, Lulu He, Ouwen Li, Shaoxuan Zhou, Yong Shi, Tong Ren, Yun-gui Yang, Quancheng Kan…

Inflammation at diagnosis and cognitive impairment two years later in breast cancer patients from the Canto-Cog study

Authors: Mylène Duivon, Justine Lequesne, Antonio Di Meglio, Caroline Pradon, Ines Vaz-Luis, Anne-Laure Martin, Sibille Everhard, Sophie Broutin, Olivier Rigal, Chayma Bousrih, Christelle Lévy, Florence Lerebours, Marie Lange and Florence Joly

Increased expression of REG3A promotes tumorigenic behavior in triple negative breast cancer cells

Authors: Xiaoxia Jin, Shuyun Yang, Xiaoyun Lu, Xudong Chen and Wencheng Dai

Alpha-6 integrin deletion delays the formation of Brca1/p53-deficient basal-like breast tumors by restricting luminal progenitor cell expansion

Authors: Marisa M. Faraldo, Mathilde Romagnoli, Loane Wallon, Pierre Dubus, Marie-Ange Deugnier and Silvia Fre

Deep learning-based risk stratification of preoperative breast biopsies using digital whole slide images

Authors: Constance Boissin, Yinxi Wang, Abhinav Sharma, Philippe Weitz, Emelie Karlsson, Stephanie Robertson, Johan Hartman and Mattias Rantalainen

Most recent articles RSS

View all articles

Serum thymidine kinase 1 activity as a pharmacodynamic marker of cyclin-dependent kinase 4/6 inhibition in patients with early-stage breast cancer receiving neoadjuvant palbociclib

Authors: Nusayba Bagegni, Shana Thomas, Ning Liu, Jingqin Luo, Jeremy Hoog, Donald W. Northfelt, Matthew P. Goetz, Andres Forero, Mattias Bergqvist, Jakob Karen, Magnus Neumüller, Edward M. Suh, Zhanfang Guo, Kiran Vij, Souzan Sanati, Matthew Ellis…

Triple-negative breast cancer molecular subtyping and treatment progress

Authors: Li Yin, Jiang-Jie Duan, Xiu-Wu Bian and Shi-cang Yu

Choosing the right cell line for breast cancer research

Authors: Deborah L Holliday and Valerie Speirs

Breast asymmetry and predisposition to breast cancer

Authors: Diane Scutt, Gillian A Lancaster and John T Manning

Critical research gaps and translational priorities for the successful prevention and treatment of breast cancer

Authors: Suzanne A Eccles, Eric O Aboagye, Simak Ali, Annie S Anderson, Jo Armes, Fedor Berditchevski, Jeremy P Blaydes, Keith Brennan, Nicola J Brown, Helen E Bryant, Nigel J Bundred, Joy M Burchell, Anna M Campbell, Jason S Carroll, Robert B Clarke, Charlotte E Coles…

Most accessed articles RSS

Editor-in-Chief

Lewis Chodosh , University of Pennsylvania, USA

Trending in the Media

Click  here  to see the most popular articles published in Breast Cancer Research  in the past three months.

BCR's 20th Anniversary

20 years ago Breast Cancer Research published its first articles with BMC. Well-respected in the field, the journal has continually placed in the first quartile of the ‘Oncology’ category of Journal Citation Reports. Over the past decade, Breast Cancer Research (BCR) has also become the highest ranked breast cancer focused title in the field.

Look back at the journal’s milestone achievements and article highlights .

Featured Review - Artificial intelligence in mammographic phenotyping of breast cancer risk: a narrative review

In this review, we provide a useful reference for AI researchers investigating image-based breast cancer risk assessment while indicating key priorities and challenges that, if properly addressed, could accelerate the implementation of AI-assisted risk stratification to future refine and individualize breast cancer screening strategies.

Springer Nature Oncology Portfolio

Discover the range of academic oncology titles at Springer Nature  here .

File(s) under embargo

until file(s) become available

A Co-design Approach to Support Oral Anticancer Medication Use in Breast Cancer

Recent developments in cancer therapeutics have allowed increased use of Oral Anticancer Medications (OAMs), including in the treatment of breast cancer. Breast cancer is the most common cancer among women in the United States. Patients with breast cancer may face key barriers in managing their OAMs at home. These challenges can lead to sub-optimal adherence and lower the overall quality of life. Designing interventions that enhance the patient experience with use of OAMs requires a deeper understanding of barriers faced by patients as they navigate their cancer care journey. The objective of this study was to identify the unmet medication management needs of patients with breast cancer who are receiving OAMs and co-design an early prototype intervention with patients to support medication management needs of patients with breast cancer.

Two phases comprise this study. Phase 1 involved patient-journey mapping to characterize the longitudinal experience of OAMs use among patients diagnosed with breast cancer. In phase 2, we conducted participatory design (PD) workshops to develop a prototype tool to address OAM needs identified in phase 1. All participants were recruited from an outpatient breast cancer clinic in Indianapolis. Eligible participants were: 18 years of age or older, diagnosed with breast cancer, and currently receiving an OAM. All participants completed a brief sociodemographic and health information questionnaire. In phase 1, enrolled persons participated in a journey mapping exercise through semi-structured interviews. Interviews were conducted either in-person or remotely via Zoom, based on participant preference. For each interview, two researchers and the participant collaborated to create individual patient journey maps to generate a concise visual storyboard focused on medication use experiences related to OAMs. The journey maps helped capture treatment timelines, key markers of medication use, and specific barriers faced by patients. Individual journey maps were consolidated to generate personas representing groups of patients with related characteristics, treatment types, goals, and unmet needs. In phase 2, three rounds of PD workshops were conducted using the focus group format to develop an early prototype intervention. In round one (inspiration stage), participants defined the problem space and prioritized a list of challenges amenable to solutions; in round two (ideation stage), participants generated multiple possible solutions and design ideas; and in round three (convergence stage), two design concepts were selected and evaluated by participants.

In phase 1, 12 interviews (11 females and 1 male) were completed. The median age of participants was 65.5 years (range, 37-75). Participants were divided into two groups based on their prescribed medication types: (1) specialty medication (palbociclib or ribociclib; n=4 patients) and (2) traditional medication (tamoxifen, anastrozole, or exemestane; n=8 patients). We defined ‘Specialty’ medications as those that require specialty pharmacies and ‘traditional’ medications as those obtainable in local community pharmacies. To represent participants across these two broad categories of medications, two personas were created. Participants who had been prescribed specialty medication reported difficulty navigating the insurance process during medication fills, while participants who prescribed traditional medication did not. Notably, the word “prior authorization” was not used by participants to explain the issues they experienced. While all participants reported having side effects from their medications, sub-optimal adherence (n=2) was reported among the traditional medication group only. Other participants taking traditional medications either found their own ways to manage side effects or simply reported: “dealing with side effects as I don’t want cancer.” Participants expressed coping with side effects by enduring them. Participants had few strategies to manage their side effects, often stating that “they didn’t think of reaching out to the doctor,” when asked. Additionally, participants mentioned needing more financial and emotional support during their treatment journey. In phase 2, each PD session was conducted with 4-5 participants and 2 researchers (the design panel). Participants identified key challenges including difficulties navigating resources and information as well as managing medication side effects. The design panel prioritized two design concepts, which were subsequently developed into two prototypes: 1) a physical breast cancer handbook; and 2) an interactive treatment navigation app for use on tablet and smartphone devices. Our team plans to consolidate, further develop, and evaluate these prototypes in subsequent work as a follow up to this pilot study.

This study provides insight into the patient experience with OAMs. The personas created can be applied in designing interventions tailored to breast cancer patients’ needs and goals, while the consolidated journey maps identify potential areas for improvement. Adequate patient education and enhanced tools and processes are necessary to manage medication side effects effectively, ultimately leading to improved medication outcomes and assisting patients in navigating their treatment. The two design concepts require further revision prior to implementation and pilot testing.

Degree Type

• Master of Science
• Pharmacy Practice

Campus location

• West Lafayette

Advisor/Supervisor/Committee Chair

Additional committee member 2, additional committee member 3, additional committee member 4, usage metrics.

• Implementation science and evaluation
• Clinical pharmacy and pharmacy practice
• Health services and systems not elsewhere classified

DigitalCommons@UNMC

Home > Eppley Institute > Theses & Dissertations

Theses & Dissertations: Cancer Research

Theses/dissertations from 2024 2024.

Novel Spirocyclic Dimer (SpiD3) Displays Potent Preclinical Effects in Hematological Malignancies , Alexandria Eiken

Dying Right: Supporting Anti-Cancer Therapy Through Immunogenic Cell Death , Elizabeth Schmitz

Therapeutic Effects of BET Protein Inhibition in B-cell Malignancies and Beyond , Audrey L. Smith

Identifying the Molecular Determinants of Lung Metastatic Adaptation in Prostate Cancer , Grace M. Waldron

Identification of Mitotic Phosphatases and Cyclin K as Novel Molecular Targets in Pancreatic Cancer , Yi Xiao

Theses/Dissertations from 2023 2023

Development of Combination Therapy Strategies to Treat Cancer Using Dihydroorotate Dehydrogenase Inhibitors , Nicholas Mullen

Overcoming Resistance Mechanisms to CDK4/6 Inhibitor Treatment Using CDK6-Selective PROTAC , Sarah Truong

Theses/Dissertations from 2022 2022

Omics Analysis in Cancer and Development , Emalie J. Clement

Investigating the Role of Splenic Macrophages in Pancreatic Cancer , Daisy V. Gonzalez

Polymeric Chloroquine in Metastatic Pancreatic Cancer Therapy , Rubayat Islam Khan

Evaluating Targets and Therapeutics for the Treatment of Pancreatic Cancer , Shelby M. Knoche

Characterization of 1,1-Diarylethylene FOXM1 Inhibitors Against High-Grade Serous Ovarian Carcinoma Cells , Cassie Liu

Novel Mechanisms of Protein Kinase C α Regulation and Function , Xinyue Li

SOX2 Dosage Governs Tumor Cell Identity and Proliferation , Ethan P. Metz

Post-Transcriptional Control of the Epithelial-to-Mesenchymal Transition (EMT) in Ras-Driven Colorectal Cancers , Chaitra Rao

Use of Machine Learning Algorithms and Highly Multiplexed Immunohistochemistry to Perform In-Depth Characterization of Primary Pancreatic Tumors and Metastatic Sites , Krysten Vance

Characterization of Metastatic Cutaneous Squamous Cell Carcinoma in the Immunosuppressed Patient , Megan E. Wackel

Visceral adipose tissue remodeling in pancreatic ductal adenocarcinoma cachexia: the role of activin A signaling , Pauline Xu

Phos-Tag-Based Screens Identify Novel Therapeutic Targets in Ovarian Cancer and Pancreatic Cancer , Renya Zeng

Theses/Dissertations from 2021 2021

Functional Characterization of Cancer-Associated DNA Polymerase ε Variants , Stephanie R. Barbari

Pancreatic Cancer: Novel Therapy, Research Tools, and Educational Outreach , Ayrianne J. Crawford

Apixaban to Prevent Thrombosis in Adult Patients Treated With Asparaginase , Krishna Gundabolu

Molecular Investigation into the Biologic and Prognostic Elements of Peripheral T-cell Lymphoma with Regulators of Tumor Microenvironment Signaling Explored in Model Systems , Tyler Herek

Utilizing Proteolysis-Targeting Chimeras to Target the Transcriptional Cyclin-Dependent Kinases 9 and 12 , Hannah King

Insights into Cutaneous Squamous Cell Carcinoma Pathogenesis and Metastasis Using a Bedside-to-Bench Approach , Marissa Lobl

Development of a MUC16-Targeted Near-Infrared Antibody Probe for Fluorescence-Guided Surgery of Pancreatic Cancer , Madeline T. Olson

FGFR4 glycosylation and processing in cholangiocarcinoma promote cancer signaling , Andrew J. Phillips

Theses/Dissertations from 2020 2020

Cooperativity of CCNE1 and FOXM1 in High-Grade Serous Ovarian Cancer , Lucy Elge

Characterizing the critical role of metabolic and redox homeostasis in colorectal cancer , Danielle Frodyma

Genomic and Transcriptomic Alterations in Metabolic Regulators and Implications for Anti-tumoral Immune Response , Ryan J. King

Dimers of Isatin Derived Spirocyclic NF-κB Inhibitor Exhibit Potent Anticancer Activity by Inducing UPR Mediated Apoptosis , Smit Kour

From Development to Therapy: A Panoramic Approach to Further Our Understanding of Cancer , Brittany Poelaert

The Cellular Origin and Molecular Drivers of Claudin-Low Mammary Cancer , Patrick D. Raedler

Mitochondrial Metabolism as a Therapeutic Target for Pancreatic Cancer , Simon Shin

Development of Fluorescent Hyaluronic Acid Nanoparticles for Intraoperative Tumor Detection , Nicholas E. Wojtynek

Theses/Dissertations from 2019 2019

The role of E3 ubiquitin ligase FBXO9 in normal and malignant hematopoiesis , R. Willow Hynes-Smith

BRCA1 & CTDP1 BRCT Domainomics in the DNA Damage Response , Kimiko L. Krieger

Targeted Inhibition of Histone Deacetyltransferases for Pancreatic Cancer Therapy , Richard Laschanzky

Human Leukocyte Antigen (HLA) Class I Molecule Components and Amyloid Precursor-Like Protein 2 (APLP2): Roles in Pancreatic Cancer Cell Migration , Bailee Sliker

Theses/Dissertations from 2018 2018

FOXM1 Expression and Contribution to Genomic Instability and Chemoresistance in High-Grade Serous Ovarian Cancer , Carter J. Barger

Overcoming TCF4-Driven BCR Signaling in Diffuse Large B-Cell Lymphoma , Keenan Hartert

Functional Role of Protein Kinase C Alpha in Endometrial Carcinogenesis , Alice Hsu

Functional Signature Ontology-Based Identification and Validation of Novel Therapeutic Targets and Natural Products for the Treatment of Cancer , Beth Neilsen

Elucidating the Roles of Lunatic Fringe in Pancreatic Ductal Adenocarcinoma , Prathamesh Patil

Theses/Dissertations from 2017 2017

Metabolic Reprogramming of Pancreatic Ductal Adenocarcinoma Cells in Response to Chronic Low pH Stress , Jaime Abrego

Understanding the Relationship between TGF-Beta and IGF-1R Signaling in Colorectal Cancer , Katie L. Bailey

The Role of EHD2 in Triple-Negative Breast Cancer Tumorigenesis and Progression , Timothy A. Bielecki

Perturbing anti-apoptotic proteins to develop novel cancer therapies , Jacob Contreras

Role of Ezrin in Colorectal Cancer Cell Survival Regulation , Premila Leiphrakpam

Evaluation of Aminopyrazole Analogs as Cyclin-Dependent Kinase Inhibitors for Colorectal Cancer Therapy , Caroline Robb

Identifying the Role of Janus Kinase 1 in Mammary Gland Development and Breast Cancer , Barbara Swenson

DNMT3A Haploinsufficiency Provokes Hematologic Malignancy of B-Lymphoid, T-Lymphoid, and Myeloid Lineage in Mice , Garland Michael Upchurch

Theses/Dissertations from 2016 2016

EHD1 As a Positive Regulator of Macrophage Colony-Stimulating Factor-1 Receptor , Luke R. Cypher

Inflammation- and Cancer-Associated Neurolymphatic Remodeling and Cachexia in Pancreatic Ductal Adenocarcinoma , Darci M. Fink

Role of CBL-family Ubiquitin Ligases as Critical Negative Regulators of T Cell Activation and Functions , Benjamin Goetz

Exploration into the Functional Impact of MUC1 on the Formation and Regulation of Transcriptional Complexes Containing AP-1 and p53 , Ryan L. Hanson

DNA Polymerase Zeta-Dependent Mutagenesis: Molecular Specificity, Extent of Error-Prone Synthesis, and the Role of dNTP Pools , Olga V. Kochenova

Defining the Role of Phosphorylation and Dephosphorylation in the Regulation of Gap Junction Proteins , Hanjun Li

Molecular Mechanisms Regulating MYC and PGC1β Expression in Colon Cancer , Jamie L. McCall

Pancreatic Cancer Invasion of the Lymphatic Vasculature and Contributions of the Tumor Microenvironment: Roles for E-selectin and CXCR4 , Maria M. Steele

Altered Levels of SOX2, and Its Associated Protein Musashi2, Disrupt Critical Cell Functions in Cancer and Embryonic Stem Cells , Erin L. Wuebben

Theses/Dissertations from 2015 2015

Characterization and target identification of non-toxic IKKβ inhibitors for anticancer therapy , Elizabeth Blowers

Effectors of Ras and KSR1 dependent colon tumorigenesis , Binita Das

Characterization of cancer-associated DNA polymerase delta variants , Tony M. Mertz

A Role for EHD Family Endocytic Regulators in Endothelial Biology , Alexandra E. J. Moffitt

Biochemical pathways regulating mammary epithelial cell homeostasis and differentiation , Chandrani Mukhopadhyay

EPACs: epigenetic regulators that affect cell survival in cancer. , Catherine Murari

Role of the C-terminus of the Catalytic Subunit of Translesion Synthesis Polymerase ζ (Zeta) in UV-induced Mutagensis , Hollie M. Siebler

LGR5 Activates TGFbeta Signaling and Suppresses Metastasis in Colon Cancer , Xiaolin Zhou

LGR5 Activates TGFβ Signaling and Suppresses Metastasis in Colon Cancer , Xiaolin Zhou

Theses/Dissertations from 2014 2014

Genetic dissection of the role of CBL-family ubiquitin ligases and their associated adapters in epidermal growth factor receptor endocytosis , Gulzar Ahmad

Strategies for the identification of chemical probes to study signaling pathways , Jamie Leigh Arnst

Defining the mechanism of signaling through the C-terminus of MUC1 , Roger B. Brown

Targeting telomerase in human pancreatic cancer cells , Katrina Burchett

The identification of KSR1-like molecules in ras-addicted colorectal cancer cells , Drew Gehring

Mechanisms of regulation of AID APOBEC deaminases activity and protection of the genome from promiscuous deamination , Artem Georgievich Lada

Characterization of the DNA-biding properties of human telomeric proteins , Amanda Lakamp-Hawley

Studies on MUC1, p120-catenin, Kaiso: coordinate role of mucins, cell adhesion molecules and cell cycle players in pancreatic cancer , Xiang Liu

Epac interaction with the TGFbeta PKA pathway to regulate cell survival in colon cancer , Meghan Lynn Mendick

Theses/Dissertations from 2013 2013

Deconvolution of the phosphorylation patterns of replication protein A by the DNA damage response to breaks , Kerry D. Brader

Modeling malignant breast cancer occurrence and survival in black and white women , Michael Gleason

The role of dna methyltransferases in myc-induced lymphomagenesis , Ryan A. Hlady

Design and development of inhibitors of CBL (TKB)-protein interactions , Eric A. Kumar

Pancreatic cancer-associated miRNAs : expression, regulation and function , Ashley M. Mohr

Mechanistic studies of mitochondrial outer membrane permeabilization (MOMP) , Xiaming Pang

Novel roles for JAK2/STAT5 signaling in mammary gland development, cancer, and immune dysregulation , Jeffrey Wayne Schmidt

Optimization of therapeutics against lethal pancreatic cancer , Joshua J. Souchek

Theses/Dissertations from 2012 2012

Immune-based novel diagnostic mechanisms for pancreatic cancer , Michael J. Baine

Sox2 associated proteins are essential for cell fate , Jesse Lee Cox

KSR2 regulates cellular proliferation, transformation, and metabolism , Mario R. Fernandez

Discovery of a novel signaling cross-talk between TPX2 and the aurora kinases during mitosis , Jyoti Iyer

Regulation of metabolism by KSR proteins , Paula Jean Klutho

The role of ERK 1/2 signaling in the dna damage-induced G2 , Ryan Kolb

Regulation of the Bcl-2 family network during apoptosis induced by different stimuli , Hernando Lopez

Studies on the role of cullin3 in mitosis , Saili Moghe

Characteristics of amyloid precursor-like protein 2 (APLP2) in pancreatic cancer and Ewing's sarcoma , Haley Louise Capek Peters

Structural and biophysical analysis of a human inosine triphosphate pyrophosphatase polymorphism , Peter David Simone

Functions and regulation of Ron receptor tyrosine kinase in human pancreatic cancer and its therapeutic applications , Yi Zou

Theses/Dissertations from 2011 2011

Coordinate detection of new targets and small molecules for cancer therapy , Kurt Fisher

The role of c-Myc in pancreatic cancer initiation and progression , Wan-Chi Lin

• Eppley Institute Website
• McGoogan Library

Advanced Search

• Notify me via email or RSS
• Collections
• Disciplines

Author Corner

Home | About | FAQ | My Account | Accessibility Statement

Privacy Copyright

Breast Cancer Research Results and Study Updates

See Advances in Breast Cancer Research for an overview of recent findings and progress, plus ongoing projects supported by NCI.

Some people with no evidence of cancer in nearby lymph nodes after presurgical chemotherapy can skip radiation to that area without increasing the risk of the cancer returning, a clinical trial found. But some experts caution that more details are needed.

For women in their 70s and older, the risk of overdiagnosis with routine screening mammography is substantial, a new study suggests. The findings highlight the need for conversations between older women and their health care providers about the potential benefits and harms of continuing screening mammography.

Many young women who are diagnosed with early-stage breast cancer want to become pregnant in the future. New research suggests that these women may be able to pause their hormone therapy for up to 2 years as they try to get pregnant without raising the risk of a recurrence in the short term.

For younger women with advanced breast cancer, the combination of ribociclib (Kisqali) and hormone therapy was much better at shrinking metastatic tumors than standard chemotherapy treatments, results from an NCI-funded clinical trial show.

In a large clinical trial, a condensed course of radiation therapy was as effective and safe as a longer standard course for those with higher-risk early-stage breast cancer who had a lumpectomy. This shorter radiation course makes treatment less of a burden for patients.

Adding the immunotherapy drug pembrolizumab (Keytruda) to chemotherapy can help some patients with advanced triple-negative breast cancer live longer. In the KEYNOTE-355 trial, overall survival improved among patients whose tumors had high levels of the PD-L1 protein.

People with metastatic breast cancer whose tumors had low levels of HER2 protein lived longer after treatment with trastuzumab deruxtecan (Enhertu) than those treated with standard chemotherapy, results of the DESTINY-Breast04 clinical trial show.

NCI researchers have shown that an experimental form of immunotherapy that uses an individual’s own tumor-fighting immune cells could potentially be used to treat people with metastatic breast cancer who have exhausted all other treatment options.

Most breast cancer risk tools were developed with data mainly from White women and don’t work as well for Black women. A new tool that estimates risk for Black women may help identify those who might benefit from earlier screening, enabling earlier diagnosis and treatment.

In people with metastatic HER2-positive breast cancer, the targeted drug trastuzumab deruxtecan (Enhertu) markedly lengthened progression-free survival compared with trastuzumab emtansine (Kadcycla), new study results show.

In a large clinical trial, women with HR-positive, HER2-negative metastatic breast cancer treated with ribociclib (Kisqali) and letrozole (Femara) as their initial treatment lived approximately 1 year longer than women treated with letrozole only.

Women with early-stage breast cancer who had one or both breasts surgically removed (a unilateral or bilateral mastectomy) had lower scores on a quality-of-life survey than women who had breast-conserving surgery, a new study has found.

For women undergoing chemotherapy for breast cancer, meeting the national physical activity guidelines may help alleviate cognitive issues, a new study suggests. The benefits may be even greater for patients who were physically active before treatment.

Sacituzumab govitecan (Trodelvy) now has regular FDA approval for people with locally advanced or metastatic triple-negative breast cancer (TNBC). The update follows last year’s accelerated approval of the drug for people with TNBC.

For some people with ER-positive breast cancer, a new imaging test may help guide decisions about receiving hormone therapy, according to a new study. The test can show whether estrogen receptors in tumors are active and responsive to estrogen.

The test, which helps guide treatment decisions, was not as good at predicting the risk of death from breast cancer for Black patients as for White patients, a new study has found. The findings highlight the need for greater racial diversity in research studies.

The drug abemaciclib (Verzenio) may be a new treatment option for people with the most common type of breast cancer, with new study findings suggesting that it can reduce the risk of the cancer returning.

Fertility preservation for young women with breast cancer doesn’t increase their risk of dying in the ensuing decades, a new study affirmed. Experts said the findings support routinely offering fertility preservation to patients who want it.

Some postmenopausal women with HR-positive, HER2-negative breast cancer may not benefit from chemotherapy and can safely forgo the treatment, according to clinical trial results presented at the San Antonio Breast Cancer Symposium.

A heart-related event, like a heart attack, may make breast cancer grow faster, a new study suggests. In mice, heart attacks accelerated breast tumor growth and human studies linked cardiac events with breast cancer recurrence, researchers reported.

FDA has approved sacituzumab govitecan (Trodelvy) for the treatment of triple-negative breast cancer that has spread to other parts of the body. Under the approval, patients must have already undergone at least two prior treatment regimens.

Women with high-risk breast cancer who engaged in regular exercise before their cancer diagnosis and after treatment were less likely to have their cancer return or to die compared with women who were inactive, a recent study found.

Researchers have developed a “microscaled” approach to analyze the proteins and genetic changes (proteogenomics) of a tumor that uses tissue from a core needle biopsy. The analyses can provide important information that may help guide treatment.

Tucatinib improved survival for women in the HER2CLIMB trial, including some whose cancer had spread to the brain. Trastuzumab deruxtecan improved survival and shrank many tumors in the DESTINY-Breast01 trial, which led to its accelerated approval.

A TAILORx analysis shows women with early-stage breast cancer and high recurrence scores on the Oncotype DX who received chemotherapy with hormone therapy had better long-term outcomes than what would be expected from hormone therapy alone.

Men with breast cancer may be more likely to die of the disease than women, particularly during the first 5 years after diagnosis, a new study suggests. The higher likelihood of death was linked in part to undertreatment and later diagnosis.

In a survey of nearly 600 breast cancer survivors, researchers found that the cost of care factored into the decisions the women made about what type of surgery to get. Many women also reported never discussing costs with their physicians.

FDA has expanded the approved use of the drug ado-trastuzumab emtansine (Kadcyla), also called T-DM1, to include adjuvant treatment in some women with early-stage HER2-positive breast cancer.

Many women diagnosed with ovarian and breast cancer are not undergoing tests for inherited genetic mutations that can provide important information to help guide decisions about treatment and longer-term cancer screening, a new study has found.

FDA has approved atezolizumab (Tecentriq) in combination with chemotherapy for the treatment of some women with advanced triple-negative breast cancer. This is the first FDA-approved regimen for breast cancer to include immunotherapy.

The build-up of connective tissue around some types of cancer can act as a barrier to immunotherapy. A new study uses a bone marrow transplant drug, plerixafor, to break down this barrier and improve the efficacy of immune checkpoint inhibitors in animal models of breast cancer.

A new study in mice shows that disrupting the relationship between breast cancer cells that spread to bone and normal cells surrounding them makes the cancer cells sensitive to treatment.

In women with early-stage breast cancer, two clinical trials have shown that both whole- and partial-breast radiation therapy are effective at preventing the cancer from returning after breast-conserving surgery.

Researchers are testing a topical-gel form of the drug tamoxifen to see if it can help prevent breast cancer as effectively as the oral form of the drug but with fewer side effects.

Findings from a clinical study and a mouse study may shed light on genetic risk factors for developing cancer-related cognitive problems in older breast cancer survivors. The results suggest a gene associated with Alzheimer’s disease may play a role.

Arsenic trioxide and retinoic acid work together to target the master regulator protein Pin1, a new study shows. In cancer cell lines and mice, the drug combination slowed the growth of triple-negative breast cancer tumors.

FDA has expanded the approved uses of ribociclib (Kisqali) for women with advanced breast cancer, including new uses in pre- and postmenopausal women. It’s the first approval under a new FDA program to speed the review of cancer drugs.

Using a liquid biopsy to test for tumor cells circulating in blood, researchers found that, in women with breast cancer, the presence of these cells could identify women at risk of their cancer returning years later.

Findings from the TAILORx clinical trial show chemotherapy does not benefit most women with early breast cancer. The new data, released at the 2018 ASCO annual meeting, will help inform treatment decisions for many women with early-stage breast cancer.

Do cancer study participants want to receive their genetic test results? A recent study involving women with a history of breast cancer tested an approach for returning genetic research results and evaluated the impact those results had on the women.

Researchers compared the risk of death for women with breast cancer who had low skeletal muscle mass, or sarcopenia, at the time of their cancer diagnosis and women who had adequate muscle mass.

Some people who have been treated for breast cancer or lymphoma have a higher risk of developing congestive heart failure than people who haven’t had cancer, results from a new study show.

FDA has approved the CDK4/6 inhibitor abemaciclib (Verzenio) as a first-line treatment in some women with advanced or metastatic breast cancer. Under the approval, the drug must be used in combination with an aromatase inhibitor.

A new study in mice raises the possibility that using microscopic, oxygen-carrying bubbles may improve the effectiveness of radiation therapy in the treatment of breast cancer.

The drug olaparib (Lynparza®) is the first treatment approved by the Food and Drug Administration for patients with metastatic breast cancer who have inherited mutations in the BRCA1 or BRCA2 genes.

Joint pain caused by aromatase inhibitors in postmenopausal women with breast cancer can cause some women to stop taking the drugs. Reducing their symptoms may translate into better adherence to therapy.

A new study suggests that the cells in treatment-resistant tumors in women with metastatic breast cancer share important characteristics that could potentially make tumors vulnerable to therapies that otherwise might not have been considered.

A large nationwide clinical trial called TMIST has been launched to compare two techniques used for mammograms: tomosynthesis, often called 3D mammography, and standard 2D digital mammography.

FDA approved abemaciclib (Verzenio™) for the treatment of some people with advanced or metastatic HR-positive, HER2-negative breast cancer whose disease has progressed after treatment with hormone therapy.

Long-term results from a large clinical trial confirm that, for some women with early-stage breast cancer who have lumpectomy as their surgical treatment, a less extensive lymph node biopsy approach is sufficient.

When given at the same time, two immune checkpoint inhibitors were ineffective against breast cancer growth in mice, a new study found. The combination was more effective and safer if the two inhibitors were given in a specific sequence.

FDA has expanded its approval of fulvestrant (Faslodex®) as a standalone treatment for postmenopausal women with advanced HR-positive, HER2-negative breast cancer who have not previously undergone endocrine therapy.

Many women who receive taxane-based chemotherapy to treat breast cancer experience long-term nerve damage, or peripheral neuropathy, data from a large clinical trial show.

Researchers recognized the potential of endoxifen as a treatment for breast cancer and, with NCI support, developed the compound into a drug now being tested in clinical trials.

Researchers have used modified stem cells to deliver a cancer drug selectively to metastatic breast cancer tumors in mice. The stem cells target metastatic tumors by homing in on the stiff environment that typically surrounds them.

FDA has approved neratinib for patients with early-stage HER2-positive breast cancer who have finished at least 1 year of adjuvant therapy with trastuzumab.

Many survivors of early-stage breast cancer prefer that their oncologist handle aspects of routine medical care usually overseen by primary care practitioners, leading to concerns about gaps in care.

Results from the first large prospective study of breast and ovarian cancer risk in women with inherited mutations in the BRCA 1 or BRCA2 genes confirm the high risks estimated from earlier, retrospective studies.

Two clinical trials show that trastuzumab emtansine (T-DM1) improves survival compared with other standard treatments for patients with HER2-positive metastatic breast cancer that has progressed after treatment with other HER2-targeted drugs.

Using one of the largest collections of tumor samples from African Americans with breast cancer, researchers tried to assess the extent to which the molecular characteristics on these tumors might help to explain breast cancer disparities.

A new study shows that the number of women in the United States living with distant metastatic breast cancer (MBC), the most severe form of the disease, is growing. This is likely due to the aging of the U.S. population and improvements in treatment.

In a randomized trial, low-income women who role-played talking with their doctor about their survivorship care plan in a counseling session reported receiving more of their recommended care than women who did not get counseling.

The FDA has approved a new targeted therapy, ribociclib, and expanded its earlier approval of another targeted therapy, palbociclib, for some women with metastatic breast cancer.

Researchers have found that duloxetine (Cymbalta®), a drug most commonly used to treat depression, may also reduce joint pain caused by aromatase inhibitors in some women being treated for early-stage breast cancer.

• MIND, BODY, WONDER

Do increased breast cancer screenings save lives? Doctors can't agree.

Breast cancer is a well-funded field of research, yet guidelines regarding additions to mammograms for women with dense breast tissue are a confusing mess.

Roughly   half of American women over 40   have what are known as dense breasts, which make screening mammograms less effective for detecting cancer. But in April the United States Preventive Services Task Force, the group charged with making public health recommendations,   stated that current evidence is insufficient   to determine whether these women might benefit from additional screening with breast ultrasonography or magnetic resonance imaging (MRI).  

The reason? Too few multi-year, randomized clinical trials have been done that show these supplemental screenings save lives,   according to the task force’s evidence review . The group made a similar finding in its prior recommendation in 2016.  

The reviewers “could not find any studies where they could clearly show whether supplemental MRI or supplemental ultrasound reported evidence of reduced progression to advanced cancer,” says John Wong, a professor of medicine at Tufts University Medical School and vice chair of the USPSTF, who helped craft the new breast cancer recommendations that also   lowered the age   most women should begin biannual screening mammograms from 50 to 40.

Dense breasts contain higher levels of fibrous and glandular tissue alongside the fat that gives breasts their size and shape. The issue of supplemental screening is important because higher density is linked to   up to six times greater risk   of developing breast cancer.  

When performing a mammogram on dense breast tissue, “there’s more interference,” says Kelsey Hampton, director of education at the Dallas-based nonprofit breast cancer research and advocacy foundation, Susan G. Komen. “It’s like trying to look through a glass jar full of clear water versus a glass jar full of water with ice cubes. You can still see things, but it’s more difficult to see with the same level of detail.” Still, she says, mammograms are important for these women.  

( When should you get screened for breast cancer—and how often? )

Introducing Nat Geo Kids Book Bundle!

Many gynecologists routinely prescribe supplemental ultrasound or MRI along with mammography in women with a dense-breast diagnosis. The task force’s new “insufficient evidence,” or “I,” rating does not mean that no women will benefit from the supplemental screening.  

“We are urgently calling for more research on whether and how additional screening might help women with dense breasts find cancers earlier,” the final recommendation statement says.

But the rating will likely confuse physicians about whether to continue prescribing the extra test and whether some insurers might drop coverage for it, says Wendie Berg, a distinguished professor of radiology at the University of Pittsburgh who   disagrees with the task force’s stance . Berg calls the task force’s I rating “stunning” because she believes current evidence is sufficient to recommend these screens.  

Amplifying the confusion: Beginning in September, the   U.S. Food and Drug Administration will require   all women getting a mammogram to be notified which of the four levels of density describe their breasts and to be advised that “in some people with dense tissue, other imaging tests in addition to a mammogram may help find cancers.”

Screening methods are underfunded

Initial studies on supplements to mammograms   go back more than 20 years . In the intervening decades, however, too little research was done to convince the USPSTF that additional screening is worthwhile.

Yet, compared to many other medical conditions, breast cancer is a well-funded field of research. The disease received more funding globally than other cancers between 2015 and 2020,   some $2.7 billion , according to a study in the   Lancet . Each year, the U.S. National Cancer Institute devotes   more than half a billion dollars   to breast cancer research, and that amount is supplemented by funding from nonprofits like Komen, which has supported more than 550 clinical trials   costing more than a billion dollars   since 1982, according to the organization.

Screening research doesn’t get the bulk of these funds, the   Lancet   study found. The vast majority went to studying cancer biology followed by drug treatment, immunotherapy, and surgery.

In making its assessment, the task force evaluated a handful of randomized screening trials that tracked the impact of supplemental screenings.

In one, for example, Japanese researchers studied a cohort of 70,000 women with all levels of breast density and randomly assigned half of them to either a group that received screening ultrasound plus mammography or just mammography alone. In the months following one round of screening, they   did not find differences   in so-called interval cancers, a measure used to demonstrate a screening tool’s potential benefit. This study is ongoing, and additional rounds of screenings could yield different results.  

You May Also Like

This is the biggest health threat to women in their 60s.

Epidurals may do more than relieve pain—they could save lives

Could menopause be delayed? The answer could lead to longer lifespans for women

Researchers in the Netherlands are also in the middle of a multi-year study. To date, they have published results from two rounds of MRI screenings that included nearly 3,500 women with extremely dense breasts whose mammograms were negative. In the second round,   six extra cancers for each thousand women   were detected. But the test also flagged 26 cases as potential cancers that were not. These false positives require unnecessary additional procedures with accompanying heightened anxiety. This rate was lower than the false positives in the first round, where nearly 80 occurred.

Increased detection rates by themselves do not indicate benefits for the techniques, Wong says. For example, if cancers that are flagged by supplemental screening are slow growing, they could likely be treated as effectively had they been caught at the next, regularly scheduled mammogram.    

“When you look harder, you are going to see more,” Wong says. “But is there definitive benefit, where patients can clearly live longer from that positive supplemental screen? We’re not there.”  

Some studies excluded

Not everyone agrees the evidence is inconclusive. The   European Society of Breast Imaging advocates   for supplemental screening with MRIs every two to four years for women with extremely dense breasts. And the   American College of Radiology recommends   women with higher than average breast cancer risk get screened annually with mammograms and supplemental MRIs.

Berg was disappointed   the task force excluded some studies   from its evaluation because they were not randomized controlled trials. One of the excluded studies involves more than a thousand women with dense breasts who have undergone two annual mammograms supplemented with an MRI. In that research,   four additional cancers were detected with MRI , many of them invasive. Other studies found screening ultrasounds   detect an additional two to three cancers per thousand on average , many of them invasive.  

Berg is convinced   all the research taken together   supports   supplemental screening, and has   created a website   to educate patients and physicians.

Some women will receive false positive results requiring unnecessary follow up, she concedes. But   in a review published in 2019   she states that careful training of technicians along with the increased use of supplementing radiologist readings with artificial intelligence can minimize this rate.

Worries about insurance

The USPSTF states that to potentially change its evaluation of additional screening in the next review cycle—likely some five years out— more studies are needed that report health outcomes   such as quality of life and mortality, especially those done in settings applicable to primary care in the U.S.  

Additional years of screening from the major ongoing studies may yield the data the task force needs, Wong says.  

In the meantime, women should speak to their healthcare practitioners to understand both their breast density level and their overall breast cancer risk, Hampton says. Density can shift over time, especially as people age, change their body weight, become pregnant or breastfeed, or take menopausal hormone therapy.

( Breast cancer spreads more aggressively during sleep )

Those with dense breasts should talk to their provider about prescribing a supplemental screen along with a mammogram, Berg says. MRI is more effective than ultrasound, but the technology is not as widely available and the cost to the patient may be higher. Some people refuse MRI screens for additional reasons. They were offered free in the Dutch study, but   40 percent of women declined , citing inconvenience, concern about the needle injection inserting the contrast material, and claustrophobia while in the machine.

In the U.S., whether supplemental screens must be covered by insurance alongside mammograms   varies by state law . Some observers worry insurers may use the USPSTF I rating as justification for change.

“There is a potential that by classifying these supplemental services as inconclusive, it could lead to insurance companies no longer covering these services,” Hampton says.

Berg believes catching breast cancer early is so important that women with dense breasts should not be dissuaded by the USPSTF rating. “A woman should have enough information to make her own choice and ask her doctor for the prescription if she wants it,” she says. “That's the bottom line.”

Related Topics

• WOMEN'S HEALTH
• HEALTH CONDITIONS
• PUBLIC HEALTH

After 30 years of decline, tuberculosis is rising in the U.S. again. How did we get here?

Oral contraceptives may help lower the risk of sports injuries

Why trigger points cause so much pain—and how you can relieve it

Why outdoor adventure is important for women as they age

Melanoma is overdiagnosed at ‘alarming’ rates. Here’s what to know.

• Environment
• Paid Content
• Photography

History & Culture

• History & Culture
• History Magazine
• Mind, Body, Wonder
• Destination Guide
• Terms of Use
• Privacy Policy
• Your US State Privacy Rights
• Children's Online Privacy Policy
• Interest-Based Ads
• About Nielsen Measurement
• Do Not Sell or Share My Personal Information
• Nat Geo Home
• Attend a Live Event
• Book a Trip
• Inspire Your Kids
• Shop Nat Geo
• Visit the D.C. Museum
• Learn About Our Impact
• Support Our Mission
• Advertise With Us
• Customer Service
• Renew Subscription
• Manage Your Subscription
• Work at Nat Geo
• Sign Up for Our Newsletters
• Contribute to Protect the Planet

Copyright © 1996-2015 National Geographic Society Copyright © 2015-2024 National Geographic Partners, LLC. All rights reserved