Overview of Early Detection for Breast Cancer: Current Status and Future Perspectives

 

Peiyan Wang1*, Jiayan Chen2, Wenyan Zhao3

 

1School of Information, University of Michigan, Ann Arbor, Michigan, USA

2Department of Radiation Oncology, Peking University First Hospital, Beijing, China

3Fielding School of Public Health, University of California, Los Angeles, California, USA

 

*Correspondence to: Peiyan Wang, School of Information, University of Michigan, 105 S State St, Ann Arbor, Michigan 48109, USA; Email: peiyanw@umich.edu

 

DOI: 10.53964/jmmo.2023010

 

Abstract

Cancer remains a formidable challenge in our modern society, and breast cancer has emerged as the most prevalent form of cancer among women worldwide. Timely detection of breast cancer holds immense potential for improving the lives of countless women globally. In this comprehensive review, we delve into the multifaceted factors that contribute to the prevalence of breast cancer among women from diverse socioeconomic backgrounds. We explored the intricate interplay of genetics, lifestyle choices, and environmental influences that contribute to breast cancer susceptibility. Additionally, we discussed the well-established screening methods, particularly mammography, which has revolutionized the early detection of breast cancer. Moreover, we highlight the advancements in the development of biomarkers that offer a simple and convenient alternative to overcome the limitations of mammography. Furthermore, we examine the pivotal role that artificial intelligence plays in enhancing breast cancer detection, presenting its potential to revolutionize diagnostic approaches and improve overall outcomes. Through this review, we aim to provide valuable insights into the various aspects of breast cancer detection, facilitating informed decision-making and advancing the fight against this formidable disease.

 

Keywords: breast cancer, early detection, risk factor, biomarkers, artificial intelligence

 

1 INTRODUCTION

Cancer poses a significant and pressing public health challenge on a global scale, with a staggering 10 million lives lost to this disease in 2020[1]. Ranking as the second leading cause of death worldwide, cancer accounts for one in every six deaths[2]. Among the various forms of cancer, breast cancer stands out as the most widespread and is responsible for the highest mortality rate among women[3]. In the United States alone, 339,250 cases of breast cancer were reported in 2022[4]. These statistics underscore the urgent need for enhanced awareness, prevention, and effective interventions to combat this pervasive disease and safeguard the well-being of individuals worldwide.

 

While effective prevention methods for breast cancer are still lacking, early detection plays a crucial role in improving outcomes and minimizing treatment costs. The utilization of mammograms and regular self-breast exams is indispensable in identifying early irregularities before tumors become advanced. In addition to these screening methods, significant advancements have been made in the development of biomarkers for early detection. These biomarkers offer non-invasive and convenient approaches to detect breast cancer at its earliest stages, enhancing the potential for successful intervention and treatment[5].

 

This review aims to provide a summary of the risk factors associated with breast cancer, as well as an overview of current and emerging methods for early detection. Furthermore, we delve into the role of artificial intelligence in the detection of breast cancer, highlighting its potential contributions to improving diagnostic accuracy and efficiency. By exploring these key aspects, we aim to contribute to the understanding of breast cancer detection strategies and pave the way for further advancements in this field.

 

2 RISK FACTORS OF BREAST CANCER

Age, familial history, and reproductive factors are among the most influential risk factors for breast cancer. Additionally, lifestyle and hormonal factors have been implicated in breast cancer risk, although the existing data is inconclusive and inconsistent[6]. A comprehensive list of the factors known to impact breast cancer risk in the population can be found in Table 1.

 

Table 1. Risk Factors Related to Breast Cancer in the World[7]

 

3 PRACTICALITIES OF SCREENING

Breast cancer currently lacks a definitive cure, highlighting the significance of secondary prevention through early detection and screening as the most practical and effective approach for women worldwide. Clinical trials have consistently demonstrated that screen-detected, nonpalpable tumors measuring ≤15mm exhibit the most favorable prognosis[8-13]. Three cost-effective, reliable, and readily available methods are currently employed for early detection and screening of breast cancer: full-field digital mammography[14,15], clinical breast exams (CBE)[16-18], and breast awareness combined with breast self-examination (BSE)[19-21]. Among these methods, mammography is the most widely utilized modality[22-24], employing low-dose X-rays of the breast[25] and serving as the initial diagnostic tool for breast cancer detection[26]. With its broad population reach, mammography remains a popular screening method for identifying initial breast cancer symptoms[27,28].

 

In addition to the standard practice of mammography screening, high-risk women can benefit from the implementation of adjunctive imaging procedures. These include ultrasound[29], breast magnetic resonance imaging (MRI)[30], breast thermography (BT)[31], positron emission tomography (PET), computed tomography (CT)[32], and histopathology (HP)[33] (Table 2). These complementary imaging techniques offer valuable insights and contribute to a more comprehensive approach in the detection and evaluation of breast abnormalities.

 

Table 2. Summary of Adjunctive Imaging Procedures

 

4 ROLE OF BIOMARKERS IN EARLY DETECTION OF BREAST CANCER

Despite the widespread use of mammogram screening for breast cancer, concerns regarding high false-positive and false-negative rates, as well as radiation exposure, have persisted[41-45]. In recent years, the advent of “omics” strategies has led to significant advancements in the quest for non-invasive biomarkers for early-stage breast cancer diagnosis. Various biomarkers, including circulating carcinoma antigens, circulating tumor cells (CTCs), circulating cell-free tumor nucleic acids (DNA or RNA), circulating microRNAs (miRNA), and circulating extracellular vesicles (EVs) in peripheral blood, nipple aspirate fluid (NAF), sweat, urine, and tears, as well as volatile organic compounds (VOCs) in breath, have emerged as potential non-invasive diagnostic markers to complement current clinical approaches and enhance early detection of breast cancer (Table 3)[46,47]. These promising biomarkers offer the potential for improved accuracy and convenience in breast cancer diagnosis, addressing some of the limitations associated with mammography.

 

Table 3. Pros and Cons of Potential Non-invasive Biomarkers for Early Detection of Breast Cancer[48]

 

Besides these non-invasive biomarkers, biopsy samples are obtained through invasive methods to determine if cells are cancerous, as well as the presence of hormone receptors and other markers influencing treatment options. Estrogen receptor alpha (ERα) and epidermal growth factor 2 (ErbB2/HER2) are key biomarkers in breast cancer. ERα is expressed in about 70% of invasive breast cancers, activating growth pathways. Progesterone receptor (PR) is also indicative of ER signaling. ER-positive or PR-positive breast cancers are treated with endocrine agents to inhibit ER signaling. ErbB2 is amplified or overexpressed in around 20% of breast cancers, with targeted therapy benefiting patients[40].

 

5 ADVANCES IN ARTIFICIAL INTELLIGENCE TECHNOLOGY IN RELATION TO EARLY DETECTION

The advent of advanced medical imaging modalities and technologies has significantly contributed to the early detection of breast cancer and the reduction of patient mortality rates. However, the interpretation of breast images remains challenging due to the inherent heterogeneity of breast tumors and fibro-glandular tissue. This heterogeneity poses obstacles in terms of achieving high sensitivity and specificity in cancer detection, leading to substantial inter-reader variability. To address these clinical challenges, researchers have dedicated their efforts to developing computer-aided detection and / or diagnosis (CAD) schemes for breast imaging, aiming to provide radiologists with decision-making support tools. Recent breakthroughs in technologies include high-throughput radiomics feature analysis and AI-based deep transfer learning. Radiomics involves extracting quantitative features from images or specific regions of interest using pattern recognition algorithms. These features provide numerical descriptions of geometrical and physical properties of the image. In oncology, features such as tumor size, shape, intensity, and texture are used to comprehensively characterize tumors, forming the radiomics signature[49]. Radiomics is based on the hypothesis that these features reflect underlying genetic and molecular mechanisms, offering insights at the epistemological level[49-53].

 

These technical progresses have facilitated the development of numerous CAD schemes and prediction models for various research tasks in breast cancer. These tasks include predicting cancer risk, assessing the likelihood of malignancy, determining tumor subtypes, staging, prognosis, and treatment response[53-55]. These advancements hold great promise in enhancing the accuracy and efficiency of breast cancer diagnosis, offering valuable support to healthcare professionals in clinical practice.

 

Although AI has made significant advancements in developing automated systems for medical image analysis and disease predictions, there are important challenges that need to be addressed before its integration into clinical practices. Limited availability of comprehensive and annotated datasets, along with the necessity for robust ethical regulations, are key concerns. Another critical issue is the “black box” nature of AI algorithms, which lack transparency and fail to provide explanations for their decisions or predictions. In breast cancer diagnosis, radiologists and physicians prefer to understand the rationale behind decisions rather than relying on opaque recommendations from AI-based systems. The lack of explainability, coupled with concerns about losing control over decision-making, often leads to skepticism among physicians regarding AI-based prediction / diagnosis systems. To gain physicians' trust and ensure the reliability of AI-driven decisions, it is crucial to provide clear explanations for the decisions made, especially in the context of disease prediction[56-58].

 

6 CONCLUSION

Breast cancer is influenced by various risk factors, including age, positive family history, obesity, and more. To screen for breast cancer, mammography, CBE, and BSE are commonly employed modalities. Among them, mammography is the most widely used. Additionally, non-invasive biomarkers offer a noninvasive and convenient approach to supplement traditional methods for early breast cancer detection. Biomarkers in biopsy provide important insights for cancer treatment and prognosis. Researchers have invested significant efforts in developing AI-powered methods for the detection and diagnosis of breast images, aiming to assist radiologists in making informed decisions. However, further research is necessary to validate these advanced techniques through large-scale trials, ensuring their effectiveness and reliability.

 

Acknowledgements

Not applicable.

 

Conflicts of Interest

The authors declared no conflict of interest.

 

Author Contribution

Wang P and Chen J wrote the manuscript. Wang P, Chen J and Zhao W contributed to the original draft preparation, review and editing. All authors read and approved the manuscript for submission.

 

Abbreviation List

ABUS, Automated breast ultrasound

BSE, Breast self-examination

BT, Breast thermography

CAD, Computer-aided detection and / or diagnosis

CBE, Clinical breast exams

CT, Computed tomography

CTC, Circulating tumor cells

DCE, Dynamic contrast-enhanced

ERα, Estrogen receptor alpha

EVs, Extracellular vesicles

HP, Histopathology

IR, Infrared

miRNA, MicroRNA

MRI, Magnetic resonance imaging

NAF, Nipple aspirate fluid

PET, Positron emission tomography

PR, Progesterone receptor

VOC, Volatile organic compounds

 

References

[1] Sung H, Ferlay J, Siegel RL et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin, 2021; 71: 209-249.[DOI]

[2] World Health Organization. Cancer. Accessed 3 February 2022. Available at:[Web]

[3] Anastasiadi Z, Lianos GD, Ignatiadou E et al. Breast cancer in young women: an overview. Updates Surg, 2017; 69: 313-317.[DOI]

[4] Giaquinto AN, Sung H, Miller KD et al. Breast Cancer Statistics, 2022. CA Cancer J Clin, 2022; 72: 524-541.[DOI]

[5] Crosby D, Bhatia S, Brindle KM et al. Early detection of cancer. Science, 2022; 375: eaay9040.[DOI]

[6] Washbrook E. Risk factors and epidemiology of breast cancer. Women's Health Med, 2006; 3: 8-14.[DOI]

[7] Momenimovahed Z, Salehiniya H. Epidemiological characteristics of and risk factors for breast cancer in the world. Breast Cancer: Targets and Therapy, 2019; 11: 151-164.[DOI]

[8] Cady B, Michaelson JS. The life-sparing potential of mammographic screening. Cancer, 2001; 91: 1699-1703.[DOI]

[9] Foster RS Jr, Lang SP, Costanza MC et al. Breast self-examination practices and breast-cancer stage. N Engl J Med, 1978; 299: 265-270.[DOI]

[10] Institute of Medicine and National Research Council. Mammography and Beyond: Developing Technologies for the Early Detection of Breast Cancer. The National Academies Press: Washington, USA, 2001.[DOI]

[11] Institute of Medicine (US) and National Research Council (US) National Cancer Policy Board, Herdman R, Lichtenfeld L, eds. Fulfilling the Potential of Cancer Prevention and Early Detection: An American Cancer Society and Institute of Medicine Symposium. The National Academies Press: Washington, USA, 2004.[DOI]

[12] Tabar L, Tony Chen HH, Amy Yen MF et al. Mammographic tumor features can predict long‐term outcomes reliably in women with 1-14‐mm invasive breast carcinoma. Cancer, 2004; 101: 1745-1759.[DOI]

[13] Smith RA, Brawley OW. The National Breast and Cervical Cancer Early Detection Program: Toward a system of cancer screening in the United States. Cancer, 2014; 120: 2617-2619.[DOI]

[14] Moghbel M, Ooi CY, Ismail N et al. A review of breast boundary and pectoral muscle segmentation methods in computer-aided detection/diagnosis of breast mammography. Artif Intell Rev, 2020; 53: 1873-1918.[DOI]

[15] Tabár L, Dean PB, Chen THH et al. The Impact of Mammography Screening on the Diagnosis and Management of Early-phase Breast Cancer. Breast Cancer, 2014; 31-78.[DOI]

[16] Simmons S. Recommended preventive services: are patients getting them? Nursing, 2013; 43: 65-67.[DOI]

[17] Duffy SW, Chen THH, Smith RA et al. Real and artificial controversies in breast cancer screening. Breast Cancer Manag, 2013; 2: 519-528.[DOI]

[18] Winchester DP. The National Accreditation Program for Breast Centers: quality improvement through standard setting. Surg Oncol Clin N Am, 2011; 20: 581-586.[DOI]

[19] Holleb AI. Purposes and goals of breast self-examination. Isr J Med Sci, 1981; 17: 839-842.

[20] Saslow D, Hannan J, Osuch J et al. Clinical breast examination: practical recommendations for optimizing performance and reporting. CA Cancer J Clin, 2004; 54: 327-344.[DOI]

[21] Madden MC, Hench LL, Hall DC et al. Model breasts for use in teaching breast self-examination. J Bioeng, 1978; 2: 427-435.

[22] Cheng H, Cai X, Chen X et al. Computer-aided detection and classification of microcalcifications in mammograms: a survey. Pattern Recogn, 2003; 36: 2967-2991.[DOI]

[23] Cheng H, Shi X, Min R et al. Approaches for automated detection and classification of masses in mammograms. Pattern Recogn, 2006; 39: 646-668.[DOI]

[24] Suh YJ, Jung J, Cho BJ. Automated Breast Cancer Detection in Digital Mammograms of Various Densities via Deep Learning. J Pers Med, 2020; 10: 211.[DOI]

[25] Mohamed AA, Berg WA, Peng H et al. A deep learning method for classifying mammographic breast density categories. Med Phys, 2018; 45: 314-321.[DOI]

[26] Mehmood M, Ayub E, Ahmad F et al. Machine Learning Enabled Early Detection of Breast Cancer by Structural Analysis of Mammograms. CMC-Comput Mater Con, 2021; 67: 641-657.[DOI]

[27] Van Ourti T, O'Donnell O, Koç H et al. Effect of screening mammography on breast cancer mortality: Quasi‐experimental evidence from rollout of the Dutch population‐based program with 17‐year follow‐up of a cohort. Int J Cancer, 2020; 146: 2201-2208.[DOI]

[28] Hong S, Song SY, Park B et al. Effect of Digital Mammography for Breast Cancer Screening: A Comparative Study of More than 8 Million Korean Women. Radiology, 2020; 294: 247-255.[DOI]

[29] Kozegar E, Soryani M, Behnam H et al. Computer aided detection in automated 3-D breast ultrasound images: a survey. Artif Intell Rev, 2020; 53: 1919-1941.[DOI]

[30] Murtaza G, Shuib L, Wahid A et al. Deep Learning-based Breast Cancer Classification through Medical Imaging Modalities: State of the Art and Research Challenges. Artif Intell Rev, 2019; 53: 1655-1720.

[31] Moghbel M, Mashohor S. A review of computer assisted detection/diagnosis (CAD) in breast thermography for breast cancer detection. Artif Intell Rev, 2013; 39: 305-313.[DOI]

[32] Domingues I, Pereira G, Martins P et al. Using deep learning techniques in medical imaging: a systematic review of applications on CT and PET. Artif Intell Rev, 2020; 53: 4093-4160.[DOI]

[33] Saha M, Chakraborty C, Racoceanu D. Efficient deep learning model for mitosis detection using breast histopathology images. Comput Med Imaging Graph, 2018; 64: 29-40.[DOI]

[34] Boca Bene I, Ciurea AI, Ciortea CA. Pros and Cons for Automated Breast Ultrasound (ABUS): a Narrative Review. J Pers Med, 2021; 11: 703.[DOI]

[35] Dong H, Kang L, Cheng S et al. Diagnostic performance of dynamic contrast‐enhanced magnetic resonance imaging for breast cancer detection: An update meta‐analysis. Thorac Cancer, 2021; 12: 3201-3207.[DOI]

[36] Turnbull LW. Dynamic contrast‐enhanced MRI in the diagnosis and management of breast cancer. NMR Biomed, 2009; 22: 28-39.[DOI]

[37] Nover AB, Jagtap S, Anjum W et al. Modern breast cancer detection: a technological review. Int J Biomed Imaging, 2009; 2009: 902326.[DOI]

[38] Gonzalez-Hernandez JL, Recinella AN, Kandlikar SG et al. Technology, application and potential of dynamic breast thermography for the detection of breast cancer. Int J Heat Mass Tran, 2019; 131: 558-573.[DOI]

[39] Reshma VK, Arya N, Ahmad SS et al. Detection of Breast Cancer Using Histopathological Image Classification Dataset with Deep Learning Techniques. Biomed Res Int, 2022; 2022: 8363850.[DOI]

[40] Waks AG, Winer EP. Breast Cancer Treatment: A Review. JAMA, 2019; 321: 288-300.[DOI]

[41] Marmot MG, Altman DG, Cameron DA et al. The benefits and harms of breast cancer screening: an independent review. Br J Cancer, 2013; 108: 2205-2240.[DOI]

[42] Stout NK, Lee SJ, Schechter CB et al. Benefits, harms, and costs for breast cancer screening after US implementation of digital mammography. J Natl Cancer Inst, 2014; 106: dju092.[DOI]

[43] Løberg M, Lousdal ML, Bretthauer M et al. Benefits and harms of mammography screening. Breast Cancer Res, 2015; 17: 1-12.[DOI]

[44] van Ravesteyn NT, Stout NK, Schechter CB et al. Benefits and harms of mammography screening after age 74 years: model estimates of overdiagnosis. J Natl Cancer Inst, 2015; 107: djv103.[DOI]

[45] van den Ende C, Oordt-Speets AM, Vroling H et al. Benefits and harms of breast cancer screening with mammography in women aged 40-49 years: A systematic review. Int J Cancer, 2017; 141: 1295-1306.[DOI]

[46] Alimirzaie S, Bagherzadeh M, Akbari MR. Liquid biopsy in breast cancer: A comprehensive review. Clin Genet, 2019; 95: 643-660.[DOI]

[47] Loke SY, Lee ASG. The future of blood-based biomarkers for the early detection of breast cancer. Eur J Cancer, 2018; 92: 54-68.[DOI]

[48] Li J, Guan X, Fan Z et al. Non-invasive Biomarkers for Early Detection of Breast Cancer. Cancers (Basel), 2020; 12: 2767.[DOI]

[49] Crivelli P, Ledda RE, Parascandolo N et al. A New Challenge for Radiologists: Radiomics in Breast Cancer. Biomed Res Int, 2018; 2018: 6120703.[DOI]

[50] Bi WL, Hosny A, Schabath MB et al. Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin, 2019; 69: 127-157.[DOI]

[51] Valdora F, Houssami N, Rossi F et al. Rapid review: radiomics and breast cancer. Breast Cancer Res Treat, 2018; 169: 217-229.[DOI]

[52] Lambin P, Leijenaar RTH, Deist TM et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol, 2017; 14: 749-762.[DOI]

[53] Tagliafico AS, Piana M, Schenone D et al. Overview of radiomics in breast cancer diagnosis and prognostication. Breast, 2020; 49: 74-80.[DOI]

[54] Jones MA, Islam W, Faiz R et al. Applying artificial intelligence technology to assist with breast cancer diagnosis and prognosis prediction. Front Oncol, 2022; 12: 980793.[DOI]

[55] Dileep G, Gianchandani Gyani SG. Artificial Intelligence in Breast Cancer Screening and Diagnosis. Cureus, 2022; 14: e30318.[DOI]

[56] Moxey A, Robertson J, Newby D et al. Computerized clinical decision support for prescribing: provision does not guarantee uptake. J Am Med Inform Assoc, 2010; 17: 25-33.[DOI]

[57] Liberati EG, Ruggiero F, Galuppo L et al. What hinders the uptake of computerized decision support systems in hospitals? A qualitative study and framework for implementation. Implement Sci, 2017; 12: 1-13.[DOI]

[58] Shah SM, Khan RA, Arif S et al. Artificial intelligence for breast cancer analysis: Trends & directions. Comput Biol Med, 2022; 142: 105221.[DOI]

 

Copyright © 2023 The Author(s). This open-access article is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, sharing, adaptation, distribution, and reproduction in any medium, provided the original work is properly cited.