Breast Cancer Screening in the Age of AI

Breast cancer remains a significant public health challenge globally, underscoring the importance of:

• Ongoing research
• Early detection through screening programs
• Advancements in personalized medicine for improved outcomes

Breast cancer is the most common cancer affecting females and ranks second after lung cancer as the leading cause of cancer-related deaths worldwide.

Understanding Causes of Breast Cancer

Breast cancer is influenced by several factors:

• Genes: BRCA1, BRCA2 mutations
• Hormones: Estrogen, progesterone, prolactin
• Environment: Exposure to pollutants like solvents, polycyclic aromatic hydrocarbons
• Lifestyle: Diet high in fat, stress, alcohol intake 

While these are known risk factors, the exact underlying cause of breast cancer remains a mystery. 

Prevalence and Incidence

The global incidence of breast cancer has seen a steady increase over the past few decades, from 26 cases per 100,000 in 2000 to 88 cases per 100,000 in 2015. The incidence and prevalence of breast cancer vary globally, reflecting the complex nature of the disease. Over the past few years, the disease has seen a significant increase in low and middle-income countries. In most African countries, breast cancer has become the most common cancer, superseding cervical cancer.

Breast Cancer Screening

• Mammography: primary screening
• Digital breast tomosynthesis (DBT): provides cross-sectional slices
• Breast MRI: complements mammography

Early detection and rapid treatment are pivotal for breast cancer control. Current screening modalities encompass a variety of approaches aimed at early detection and improved outcomes. Mammography is the screening test most familiar to the general population. It offers a well-established method for detecting breast cancer and remains the primary screening method.

Recently, digital breast tomosythesis (DBT) has emerged as a promising screening modality, as it provides multiple cross-sectional slices for each breast. Additionally, breast MRI have been explored to complement mammography and improve overall cancer detection rates, particularly for women at increased risk of breast cancer.

The Role of Artificial Intelligence (AI)

AI has had a significant impact on the screening process for breast cancer, transforming early detection and diagnosis. AI systems utilize deep learning and neural networks to analyze mammograms. 

AI algorithms have transformed breast cancer screening by:

• Enhancing accuracy and efficiency
• Providing valuable insights to radiologists
• Improving cancer detection rates 

Key applications of AI for mammogram analysis:

• Integrated AI readers collaborate with radiologists for mammogram interpretation
• Classification algorithms analyze benign vs. cancerous growths
• Computer-aided detection/risk prediction validated by AI
• Demonstrated potential to reduce over-diagnosis and interval cancers

Additionally, AI algorithms have been employed to classify breast masses, improving the diagnostic capabilities of healthcare providers and providing a more detailed analysis of benign and cancerous growths. Moreover, AI has played a crucial role in externally validating computer-aided systems for breast cancer detection and risk prediction based on screening mammography. These AI algorithms, supported by cloud computing technologies, provide triage detection and diagnosis capabilities, which contribute to improved patient outcomes.

The use of AI in breast cancer screening also has the potential to enhance cancer detection rates and reduce over-diagnosis. Furthermore, AI-driven systems have been developed to combine automated 3D breast ultrasound and mammograms for detecting breast cancer in women with dense breasts. 

Future Directions

Future prospects of breast cancer screening using AI hold great promise in revolutionizing early detection and diagnosis. AI applications in breast cancer screening are rapidly advancing, with the potential to significantly enhance the accuracy and efficiency of screening programs. 

AI algorithms offer:

• Risk stratification
• Individualized screening strategies
• Enhanced early detection capabilities 

AI in mammography interpretation has been shown to perform at or above the level of human radiologists. AI-driven systems have also been shown to interval cancer risk in women with negative screening mammograms.

The future of breast cancer screening using AI also involves leveraging advanced technologies such as deep learning and model training to enhance early detection capabilities. AI-assisted risk stratification and individualized screening strategies are being explored to refine breast cancer screening practices and improve patient outcomes.

The integration of AI in breast cancer care is expected to accelerate the development of innovative screening tools and improve the overall quality of screening programs. As AI continues to evolve, future research will focus on refining screening protocols and optimizing cancer detection rates.

Written by Alexander Habte Habtemariam MD

Edited by Nancy Guillaume

References

1. Corradini A, Cremonini AL, Cattani MG, et al. Which Type of Cancer Is Detected in Breast Screening Programs? Review of the Literature With Focus on the Most Frequent Histological Features. Pathologica. Published online 2021. doi:10.32074/1591-951x-123
2. Manning HC, Buck JR, Cook RS. Mouse Models of Breast Cancer: Platforms for Discovering Precision Imaging Diagnostics and Future Cancer Medicine. J Nucl Med. Published online 2016. doi:10.2967/jnumed.115.157917
3. Brandao DF, Strasser‐Weippl K, Goss PE. Prolactin and Breast Cancer: The Need to Avoid Undertreatment of Serious Psychiatric Illnesses in Breast Cancer Patients: A Review. Cancer. Published online 2015. doi:10.1002/cncr.29714
4. Sn R, Atoum M, Al-Hourani HM, Rasheed M, Nimer N, Almuhrib T. Relationship Between Plasma Progesterone, Estradiol and Prolactin Concentrations and Breast Cancer in Pre and Postmenopausal Women. Neoplasma. Published online 2010. doi:10.4149/neo_2010_01_074
5. Brody JG, Rudel RA. Environmental Pollutants and Breast Cancer. Environ Health Perspect. Published online 2003. doi:10.1289/ehp.6310
6. Wang HH, Chung UL. Relationships Between Cause of Cancer and Breast Cancer-Related Factors in Breast Cancer Survivors. Asian Pac J Cancer Prev. Published online 2012. doi:10.7314/apjcp.2012.13.8.3889
7. Kim D hoon, Chung J, Cha ES, Lee JE, Kim JH. Digital Breast Tomosynthesis as a Breast Cancer Screening Tool for Women With Gynecologic Cancer. J Korean Soc Radiol. Published online 2020. doi:10.3348/jksr.2020.81.4.886
8. Pace LE, Shulman LN. Breast Cancer in Sub-Saharan Africa: Challenges and Opportunities to Reduce Mortality. The Oncologist. Published online 2016. doi:10.1634/theoncologist.2015-0429
9. Dileep G, Gianchandani Gyani SG. Artificial Intelligence in Breast Cancer Screening and Diagnosis. Cureus. Published online 2022. doi:10.7759/cureus.30318
10. Machida Y, Tozaki M, Shimauchi A, Yoshida T. Breast Density: The Trend in Breast Cancer Screening. Breast Cancer. Published online 2015. doi:10.1007/s12282-015-0602-2
11. Mahon SM. Screening for Breast Cancer: Evidence and Recommendations. Clin J Oncol Nurs. Published online 2012. doi:10.1188/12.cjon.567-571
12. Frazer H, Peña-Solórzano CA, Kwok CF, et al. Integrated AI Reader Development and Evaluation Provides Clinically-Relevant Guidance for Human-Ai Collaboration in Population Mammographic Screening. Published online 2022. doi:10.1101/2022.11.23.22282646
13. Liu Q, Qu M, Sun LZ, Wang H. Accuracy of Ultrasonic Artificial Intelligence in Diagnosing Benign and Malignant Breast Diseases. Medicine (Baltimore). Published online 2021. doi:10.1097/md.0000000000028289
14. Cossio FP, Schurz H, Engström M, et al. VAI-B: A Multicenter Platform for the External Validation of Artificial Intelligence Algorithms in Breast Imaging. J Med Imaging. Published online 2023. doi:10.1117/1.jmi.10.6.061404
15. Marinovich ML, Wylie E, Lotter W, et al. Artificial intelligence (AI) for breast cancer screening: BreastScreen population-based cohort study of cancer detection. Ebiomedicine. 2023;90. Accessed January 24, 2024. https://www.thelancet.com/journals/ebiom/article/PIIS2352-3964(23)00063-4/fulltext
16. Tan T, Rodriguez-Ruiz A, Zhang T, et al. Multi-Modal Artificial Intelligence for the Combination of Automated 3D Breast Ultrasound and Mammograms in a Population of Women With Predominantly Dense Breasts. Insights Imaging. Published online 2023. doi:10.1186/s13244-022-01352-y
17. Lång K, Hofvind S, Rodríguez‐Ruiz A, Andersson I. Can Artificial Intelligence Reduce the Interval Cancer Rate in Mammography Screening? Eur Radiol. Published online 2021. doi:10.1007/s00330-021-07686-3
18. Freeman K, Geppert J, Stinton C, et al. Use of Artificial Intelligence for Image Analysis in Breast Cancer Screening Programmes: Systematic Review of Test Accuracy. BMJ. Published online 2021. doi:10.1136/bmj.n1872
19. van Winkel SL, Rodriguez-Ruiz A, Appelman L, et al. Impact of Artificial Intelligence Support on Accuracy and Reading Time in Breast Tomosynthesis Image Interpretation: A Multi-Reader Multi-Case Study. Eur Radiol. Published online 2021. doi:10.1007/s00330-021-07992-w
20. Gonzales K, Harding AK, Lambert WE, Fu R, Henderson WG. Perceived Experiences of Discrimination in Health Care: A Barrier for Cancer Screening Among American Indian Women With Type 2 Diabetes. Women Health Issues. Published online 2013. doi:10.1016/j.whi.2012.10.004
21. Spangler L, Yu O, Loggers ET, Boudreau DM. Bone Mineral Density Screening Among Women With a History of Breast Cancer Treated With Aromatase Inhibitors. J Women Health. Published online 2013. doi:10.1089/jwh.2012.3687
22. Ferreira MF, Savoy JN, Markey MK. Teaching Cross-Cultural Design Thinking for Healthcare. The Breast. Published online 2020. doi:10.1016/j.breast.2019.12.015
23. Cushnan D, Young KC, Ward D, et al. Lessons Learned From Independent External Validation of an AI Tool to Detect Breast Cancer Using a Representative UK Data Set. Br J Radiol. Published online 2023. doi:10.1259/bjr.20211104
24. All illustrations and images in this document are sourced from the iStock website (www.istockphoto.com) and used under a standard license agreement.