Deep Learning and CAD Systems in Breast Cancer Detection A Systematic Review of Diagnostic Accuracy and Clinical Integration

Abstract

Breast cancer continues to be a significant health challenge for women worldwide, and early detection is essential for improving survival outcomes. Over the years, Computer-Aided Diagnosis (CAD) systems have supported radiologists by highlighting suspicious regions in mammograms, ultrasound images, and magnetic resonance imaging (MRI). However, traditional CAD systems evaluate image features based on predefined rules and are associated with high false-positive rates, limiting their ability to adapt to new or complex cases. This study aimed to examine the role of deep learning (DL) in the development of computer-aided diagnosis (CAD) systems and to evaluate the diagnostic accuracy and clinical integration of AI-based approaches in breast cancer detection. A systematic review was conducted by analyzing 13 studies published between 2000 and 2024. Relevant studies were identified through a comprehensive search of the PubMed, IEEE Xplore, and Scopus databases. The included studies were evaluated according to their methodology, deep learning architectures including Convolutional Neural Networks (CNNs), ResNet, EfficientNet, and Vision Transformers and their reported diagnostic performance in terms of accuracy, sensitivity, specificity, and false-negative reduction. The findings were synthesized narratively to compare the advantages and limitations of AI-based diagnostic systems with traditional CAD systems. The findings demonstrate that DL-based models outperform traditional CAD systems. These models contribute to earlier diagnosis by detecting subtle lesions, microcalcifications, and asymmetrical structures that may be overlooked by the human eye. However, several challenges remain, including the availability of large, high-quality datasets, the interpretability of AI decisions, ethical considerations, and integration into routine clinical practice. Deep learning-enhanced CAD systems represent a promising advancement in breast cancer diagnosis by improving diagnostic performance and supporting clinical decision-making. However, their successful implementation depends on high-quality data, transparent and interpretable models, and appropriate ethical and regulatory frameworks to ensure that AI serves as a supportive tool that complements, rather than replaces, radiologists.

Keywords

• Deep learning
• CAD systems
• breast cancer
• artificial intelligence
• clinical application

Meme Kanseri Tanısında Derin Öğrenme ve CAD Sistemleri: Tanısal Doğruluk ve Klinik Entegrasyonun Sistematik İncelemesi

Abstract

Meme kanseri, dünya çapında kadınlar için önemli bir sağlık sorunu olmaya devam etmekte olup, erken teşhis sağkalım sonuçlarının iyileştirilmesi açısından kritik öneme sahiptir. Yıllar boyunca Bilgisayar Destekli Tanı (CAD) sistemleri, mamografi, ultrason ve manyetik rezonans görüntüleme (MRG) incelemelerinde şüpheli bölgeleri belirleyerek radyologlara destek olmuştur. Bununla birlikte, geleneksel CAD sistemleri görüntü özelliklerini önceden tanımlanmış kurallara göre değerlendirmekte ve yüksek yanlış pozitif oranları nedeniyle yeni veya karmaşık olgulara uyum sağlamada sınırlılıklar göstermektedir. Bu çalışmanın amacı, derin öğrenmenin (DL) bilgisayar destekli tanı (CAD) sistemlerinin geliştirilmesindeki rolünü incelemek ve yapay zekâ tabanlı yaklaşımların meme kanseri tanısındaki tanısal doğruluğunu ve klinik entegrasyonunu değerlendirmektir. PubMed, IEEE Xplore ve Scopus veri tabanlarında 2000–2024 yılları arasında yayımlanan çalışmalar sistematik olarak tarandı. Dahil edilme kriterlerini karşılayan 13 çalışma incelemeye alındı. Çalışmalar, metodolojik özellikleri, kullanılan derin öğrenme mimarileri (Evrişimsel Sinir Ağları, ResNet, EfficientNet ve Vision Transformers) ile doğruluk, duyarlılık, özgüllük ve yanlış negatif oranları açısından değerlendirildi. Bulgular, yapay zekâ tabanlı tanı sistemlerinin geleneksel CAD sistemlerine göre avantajlarını ve sınırlılıklarını karşılaştırmak amacıyla anlatımsal olarak sentezlendi. Bulgular, DL tabanlı modellerin geleneksel CAD sistemlerine kıyasla üstün performans sergilediğini göstermektedir. Bu modeller, radyologlar tarafından gözden kaçabilecek ince lezyonları, mikrokalsifikasyonları ve asimetrik yapıları tespit ederek erken tanıya katkı sağlamaktadır. Bununla birlikte, büyük ve yüksek kaliteli veri setlerine erişim, yapay zekâ kararlarının yorumlanabilirliği, etik konular ve rutin klinik uygulamaya entegrasyon gibi önemli zorluklar devam etmektedir. Derin öğrenme ile güçlendirilmiş bilgisayar destekli tanı (CAD) sistemleri, tanısal performansı artırarak ve klinik karar verme süreçlerini destekleyerek meme kanseri tanısında umut verici bir gelişme sunmaktadır. Bununla birlikte, bu sistemlerin başarılı bir şekilde klinik uygulamaya geçirilmesi; yüksek kaliteli veri kullanımına, şeffaf ve yorumlanabilir modellerin geliştirilmesine ve uygun etik ile düzenleyici çerçevelerin oluşturulmasına bağlıdır. Yapay zekâ, radyologların yerini alan değil, klinik karar vermeyi destekleyen tamamlayıcı bir araç olarak kullanılmalıdır.

Keywords

• Derin öğrenme
• CAD sistemleri
• meme kanseri
• yapay zekâ
• klinik uygulama

References

1. 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(3):209-249.
2. 2. DeSantis CE, Ma J, Gaudet MM, et al. Breast cancer statistics, 2019. CA Cancer J Clin. 2019;69(6):438-451.
3. 3. Rodríguez-Ruiz A, Krupinski E, Mordang JJ, et al. Detection of breast cancer with mammography: effect of an artificial intelligence support system. Radiology. 2019;290(2):305-314. doi: 10.1148/radiol.2018181371.
4. 4. Dang LA, Chazard E, Poncelet E, et al. Impact of artificial intelligence in breast cancer screening with mammography. Breast Cancer. 2022;29(6):967-977.
5. 5. Lång K, Andersson I, Rosso A, Tingberg A, Timberg P, Zackrisson S. Artificial intelligence-supported screen reading versus standard double reading in the Mammography Screening with Artificial Intelligence (MASAI) trial: A clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study. Lancet Oncol. 2023;24(8):936-944.
6. 6. Goodfellow I, Bengio Y, Courville A. Deep Learning. MIT Press; 2016.
7. 7. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25:1097-1105.
8. 8. Sahiner B, Pezeshk A, Hadjiiski LM, et al. Deep learning in medical imaging and radiology. Med Phys. 2019;46(1):e1-e36.

9. 9. McKinney SM, Sieniek M, Godbole V, et al. International evaluation of an AI system for breast cancer screening. Nature. 2020;577(7788):89-94.
10. 10. Ribli D, Horváth A, Unger Z, et al. Detecting and classifying lesions in mammograms with deep learning. Sci Rep. 2018;8:4165.
11. 11. Rodríguez-Ruiz A, Lång K, Gubern-Mérida A, et al. Stand-alone artificial intelligence for breast cancer detection. Radiology. 2019;290(2):305-314.
12. 12. Schaffter T, Buist DSM, Lee CI, et al. Evaluation of combined artificial intelligence and radiologist assessment to interpret screening mammograms. JAMA Netw Open. 2020;3(3):e200265.
13. 13. Yala A, Lehman C, Schuster T, Portnoi T, Barzilay R. A deep learning mammography-based model for improved breast cancer risk prediction. Radiology. 2019;292(1):60-66.
14. 14. Boyd NF, Guo H, Martin LJ, et al. Mammographic density and the risk and detection of breast cancer. N Engl J Med. 2007;356(3):227-236.
15. 15. Lauritzen AD, Lång K, von Euler-Chelpin M, Andersson I, Zackrisson S, Rodríguez-Ruiz A. AI-integrated screening to replace double reading of mammograms: A population-wide accuracy and feasibility study. Radiol Artif Intell. 2024;6(3):e230529.
16. 16. Liu X, Faes L, Kale AU, et al. A comparison of deep learning performance against health-care professionals. Lancet Digit Health. 2019;1(6):e271-e297.
17. 17. Wang J, Yang X, Cai H, et al. Discrimination of breast cancer with CNN-based classification. Comput Methods Programs Biomed. 2016;134:47-55.
18. 18. Kooi T, Litjens G, van Ginneken B, et al. Large-scale deep learning for computer-aided detection of mammographic lesions. Med Image Anal. 2017;35:303–312.
19. 19. Lauritzen AD, Rodríguez-Ruiz A, von Euler-Chelpin MC, et al. An artificial intelligence-based mammography screening protocol for breast cancer: Outcome and radiologist workload. Radiology. 2022;304(1):41-49. doi:10.1148/radiol.210948
20. 20. Kim HE, Kim HH, Han BK, et al. Changes in cancer detection and false-positive recall after AI support. Radiology. 2020;294(1):38-49.
21. 21. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56.
22. 22. Ahmad OF, Stoyanov D, Lovat LB. Artificial intelligence for clinical decision support. BMJ. 2020;368:m121.
23. 23. Lotter W, Diab AR, Haslam B, et al. Robust breast cancer detection in mammography and digital breast tomosynthesis using an annotation-efficient deep learning approach. Nat Med. 2021;27(2):244-249.
24. 24. Lehman CD, Yala A, Schuster T, et al. Mammographic breast density assessment using deep learning. Radiology. 2019;290(1):38-46.
25. 25. Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60-88.
26. 26. Elhakim MT, Stougaard SW, Graumann O, et al. AI-integrated screening to replace double reading of mammograms: A population-wide accuracy and feasibility study. Radiol Artif Intell. 2024;6(6):e230529.
27. 27. Kim HE, Kim HH, Han BK, et al. Artificial intelligence for breast cancer screening in mammography (AI-STREAM): Preliminary analysis of a prospective multicenter cohort study. Nat Commun. 2025;16:1897.
28. 28. Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71.
29. 29. European Commission. Ethics Guidelines for Trustworthy AI. European Commission; 2019.
30. 30. US Food and Drug Administration. Artificial intelligence and machine learning in medical devices. FDA; 2021.