Enter your email address
Submit
Write your message
Volume 19, Issue 1 (Iranian Journal of Breast Diseases 2026)
ijbd 2026, 19(1): 31-48 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Samadi Z, Norouzi M, Shahdi S O, Haddad Zahmatkesh M. Automatic Detection of Breast Cancer from Digital Mammography Images By YOLO Artificial Intelligence Algorithm. ijbd 2026; 19 (1) :31-48
URL: http://ijbd.ir/article-1-1230-en.html
URL: http://ijbd.ir/article-1-1230-en.html
1- Department of Biomedical Engineering, Qa.c., Islamic Azad University, Qazvin, Iran
2- Department of Electrical Engineering, Qa.C., Islamic Azad University, Qazvin, Iran ,mh.norouzi@iau.ir
3- Department of Electrical Engineering, Qa.C., Islamic Azad University, Qazvin, Iran
4- Department of Pharmaceutical Biotechnology-Nuclear Pharmacy, School of Pharmacy, Guilan University of Medical Sciences, Rasht, Iran
2- Department of Electrical Engineering, Qa.C., Islamic Azad University, Qazvin, Iran ,
3- Department of Electrical Engineering, Qa.C., Islamic Azad University, Qazvin, Iran
4- Department of Pharmaceutical Biotechnology-Nuclear Pharmacy, School of Pharmacy, Guilan University of Medical Sciences, Rasht, Iran
Abstract: (601 Views)
Introduction: Early detection of breast cancer in digital mammography remains technically challenging, particularly for small or low-contrast lesions embedded within dense fibroglandular tissue. Structural noise and subtle lesion margins often reduce localization accuracy and increase false-negative interpretations in screening settings. To address these limitations, this study proposes a lightweight object-detection framework based on YOLOv11n, enhanced with targeted preprocessing and heatmap-guided spatial attention to improve lesion detectability and localization precision.
Methods: Digital mammography images from the VinDr-Mammo dataset were used for model development and evaluation under standardized training conditions. The proposed framework incorporated contrast-limited adaptive histogram equalization (CLAHE), bilateral filtering, and spatial attention guidance during training. Performance was quantitatively assessed using Precision, Recall, mean Average Precision (mAP@0.5 and mAP@0.5:0.95), and inference time, and compared against YOLOv5, YOLOv8, EfficientDet-D0, and Faster R-CNN.
Results: The YOLOv11n-based framework achieved precision of 70.24%, recall of 68.01%, mAP@0.5 of 68.28%, and mAP@0.5:0.95 of 40.82%. Compared with reference models, the proposed approach improved mAP@0.5 by 6–9% and Recall by 5–7%, while maintaining real-time inference speed (<40 ms per image). The increase in Recall reflects a measurable reduction in false-negative detections, which is clinically relevant for early-stage lesion identification. Concurrently, the maintained Precision indicates controlled false-positive rates, supporting the practical applicability of screening.
Conclusion: The proposed YOLOv11n-based framework demonstrates robust detection performance and real-time feasibility, suggesting its potential as a pre-clinical decision-support module for mammography CAD systems. However, external multi-center validation, radiologist-in-the-loop studies, and workflow integration assessment are required before clinical deployment.
Methods: Digital mammography images from the VinDr-Mammo dataset were used for model development and evaluation under standardized training conditions. The proposed framework incorporated contrast-limited adaptive histogram equalization (CLAHE), bilateral filtering, and spatial attention guidance during training. Performance was quantitatively assessed using Precision, Recall, mean Average Precision (mAP@0.5 and mAP@0.5:0.95), and inference time, and compared against YOLOv5, YOLOv8, EfficientDet-D0, and Faster R-CNN.
Results: The YOLOv11n-based framework achieved precision of 70.24%, recall of 68.01%, mAP@0.5 of 68.28%, and mAP@0.5:0.95 of 40.82%. Compared with reference models, the proposed approach improved mAP@0.5 by 6–9% and Recall by 5–7%, while maintaining real-time inference speed (<40 ms per image). The increase in Recall reflects a measurable reduction in false-negative detections, which is clinically relevant for early-stage lesion identification. Concurrently, the maintained Precision indicates controlled false-positive rates, supporting the practical applicability of screening.
Conclusion: The proposed YOLOv11n-based framework demonstrates robust detection performance and real-time feasibility, suggesting its potential as a pre-clinical decision-support module for mammography CAD systems. However, external multi-center validation, radiologist-in-the-loop studies, and workflow integration assessment are required before clinical deployment.
Type of Study: Research |
Subject:
Diagnosis, treatment, rehabilitation
Received: 2025/12/4 | Accepted: 2026/02/16 | Published: 2026/03/25
Received: 2025/12/4 | Accepted: 2026/02/16 | Published: 2026/03/25
References
1. Thomas NS, Norris E. Understanding the delays in diagnosis of breast cancer in India using blogs and YouTube videos. BMC Public Health. 2025;25(1):2792. DOI: 10.1186/s12889-025-24132-x. [DOI:10.1186/s12889-025-24132-x] [PMID] []
2. Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, Jemal A. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians. 2024;74(3):229-63. DOI: 10.3322/caac.21834. [DOI:10.3322/caac.21834] [PMID]
3. Brockton NT, Cook LS, Magliocco AM, Shemanko CS, Vogel HJ, Khan M, Kopciuk KA. The Breast to Bone (B2B) Cohort Study to Prevent, Detect and Improve Treatment of Metastatic Disease: Baseline Assessment, Description and Progress. International Journal of Environmental Research and Public Health. 2025;22(2):242. DOI: 10.3390/ijerph22020242. [DOI:10.3390/ijerph22020242] [PMID] []
4. Rahimzadeh S, Bentham J, Burczynska B, Farzadfar F, Di Cesare M. Spatiotemporal disparity of breast cancer incidence in Iranian female populations at the district level from 2000 to 2021: Bayesian disease mapping. Plos one. 2025;20(9):e0330017. DOI: 10.1371/journal.pone.0330017 [DOI:10.1371/journal.pone.0330017] [PMID] []
5. Shi J, Li J, Gao Y, Chen W, Zhao L, Li N, Tian J, Li Z. The screening value of mammography for breast cancer: an overview of 28 systematic reviews with evidence mapping. Journal of Cancer Research and Clinical Oncology. 2025;151(3):1-20. DOI: 10.1007/s00432-025-06122-z. [DOI:10.1007/s00432-025-06122-z] [PMID] []
6. Koninckx P, Ussia A, Page G. Breast cancer screening in women taking hormone replacement therapy needs updating. Authorea Preprints. 2023;10. DOI: 10.52054/FVVO.16.1.001. [DOI:10.52054/FVVO.16.1.001] [PMID] []
7. Ciurescu S, Cerbu S, Dima CN, Borozan F, Pârvănescu R, Ilaș DG, Cîtu C, Vernic C, Sas I. AI in 2D Mammography: Improving Breast Cancer Screening Accuracy. Medicina. 2025;61(5):809. DOI: 10.3390/medicina61050809. [DOI:10.3390/medicina61050809] [PMID] []
8. Pasokh Z, Mazidimoradi A, Hamidian M, Shahabinia Z, Kiani M, Salehiniya H. National and Subnational Burden of Female Breast Cancer in Iran from 2010 to 2021. Diseases. 2025;14(1):15. DOI: 10.3390/diseases14010015. [DOI:10.3390/diseases14010015] [PMID] []
9. Dadzie AK, Iddir SP, Ganesh S, Ebrahimi B, Rahimi M, Abtahi M, Son T, Heiferman MJ, Yao X. Artificial intelligence in the diagnosis of uveal melanoma: advances and applications. Experimental Biology and Medicine. 2025;250:10444. DOI: 10.3389/ebm.2025.10444 [DOI:10.3389/ebm.2025.10444] [PMID] []
10. Hadjiiski L, Cha K, Chan HP, Drukker K, Morra L, Näppi JJ, Sahiner B, Yoshida H, Chen Q, Deserno TM, Greenspan H. AAPM task group report 273: recommendations on best practices for AI and machine learning for computer‐aided diagnosis in medical imaging. Medical physics. 2023;50(2):e1-24. DOI: 10.1002/mp. 16188. [DOI:10.1002/mp.16188] []
11. Jailin C, Mohamed S, Iordache R, Milioni De Carvalho P, Ahmed SY, Abdel Sattar EA, Moustafa AF, Gomaa MM, Kamal RM, Vancamberg L. AI-based cancer detection model for contrast-enhanced mammography. Bioengineering. 2023;10(8):974. DOI: 10.3390/bioengineering10080974. [DOI:10.3390/bioengineering10080974] [PMID] []
12. Yuan M, Zhang C, Wang Z, Liu H, Pan G, Tang H. Trainable spiking-YOLO for low-latency and high-performance object detection. Neural Networks. 2024;172:106092. DOI: 10.1016/j.neunet.2023.106092. [DOI:10.1016/j.neunet.2023.106092] [PMID]
13. Mao M, Hong M. YOLO object detection for real-time fabric defect inspection in the textile industry: A review of YOLOv1 to YOLOv11. Sensors (Basel, Switzerland). 2025;25(7):2270. DOI: 10.3390/s25072270. [DOI:10.3390/s25072270] [PMID] []
14. Obuchowicz B, Zarzecka J, Strzelecki M, Jakubowska M, Obuchowicz R, Piórkowski A, Zarzecka-Francica E, Lasek J. Improving endodontic radiograph interpretation with TV-CLAHE for enhanced root canal detection. Journal of Clinical Medicine. 2025;14(15):5554. DOI: 10.3390/jcm14155554. [DOI:10.3390/jcm14155554] [PMID] []
15. Maus J, Nikulin P, Hofheinz F, Petr J, Braune A, Kotzerke J, van den Hoff J. Deep learning based bilateral filtering for edge-preserving denoising of respiratory-gated PET. EJNMMI physics. 2024;11(1):58. DOI: 10.1186/s40658-024-00661-z. [DOI:10.1186/s40658-024-00661-z] [PMID] []
16. Kernick K, Woudstra R, Berjanskii M, MacKay S, Wishart DS. Heatmapper2: web-enabled heat mapping made easy. Nucleic Acids Research. 2025:gkaf385. DOI: 10.1093/nar/gkaf385 [DOI:10.1093/nar/gkaf385] [PMID] []
17. Nguyen HT, Nguyen HQ, Pham HH, Lam K, Le LT, Dao M, Vu V. VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography. Scientific Data. 2023;10(1):277. DOI: 10.1038/s41597-023-02100-7. [DOI:10.1038/s41597-023-02100-7] [PMID] []
18. Sun K, Tang M, Li S, Tong S. Mildew detection in rice grains based on computer vision and the YOLO convolutional neural network. Food Science & Nutrition. 2024;12(2):860-8. DOI: 10.1002/fsn3.3798. DOI: 10.3390/diagnostics14242875. [DOI:10.1002/fsn3.3798] [PMID] []
19. Shia WC, Ku TH. Enhancing Microcalcification Detection in Mammography with YOLO-v8 Performance and Clinical Implications. Diagnostics. 2024;14(24):2875. DOI: 10.3390/diagnostics14242875. [DOI:10.3390/diagnostics14242875] [PMID] []
20. Karako K, Mihara Y, Arita J, Ichida A, Bae SK, Kawaguchi Y, Ishizawa T, Akamatsu N, Kaneko J, Hasegawa K, Chen Y. Automated liver tumor detection in abdominal ultrasonography with a modified faster region-based convolutional neural networks (Faster R-CNN) architecture. Hepatobiliary Surgery and Nutrition. 2022;11(5):675. DOI: 10.21037/hbsn-21-43. [DOI:10.21037/hbsn-21-43] [PMID] []
21. Nawaz M, Nazir T, Baili J, Khan MA, Kim YJ, Cha JH. CXray-EffDet: Chest disease detection and classification from X-ray images using the EfficientDet model. Diagnostics. 2023;13(2):248. DOI: 10.3390/diagnostics13020248. [DOI:10.3390/diagnostics13020248] [PMID] []
22. Carriero A, Groenhoff L, Vologina E, Basile P, Albera M. Deep learning in breast cancer imaging: State of the art and recent advancements in early 2024. Diagnostics. 2024;14(8):848. DOI: 10.3390/diagnostics14080848. [DOI:10.3390/diagnostics14080848] [PMID] []
23. Perez-Nunez JR, Rodriguez C, Vasquez-Serpa LJ, Navarro C. The challenge of deep learning for the prevention and automatic diagnosis of breast cancer: A systematic review. Diagnostics. 2024;14(24):2896. DOI: 10.3390/diagnostics14242896. [DOI:10.3390/diagnostics14242896] [PMID] []
24. Amin A, Koteshwara P, PC S, Mathew S. A systematic literature review on mammography: deep learning techniques for breast cancer detection with global and Asian perspectives. BMC Cancer. 2025 Dec;25(1):1-23. DOI: 10.1186/s12885-025-14876-5. [DOI:10.1186/s12885-025-14876-5] [PMID] []
25. Lam QT, Le MH, Lee IT, Le NQ. Evaluating YOLO for dental caries diagnosis: a systematic review and meta-analysis. Evidence-Based Dentistry. 2025:1-4. DOI: 10.1038/s41432-025-01180-1 [DOI:10.1038/s41432-025-01180-1] [PMID]
26. Ciurescu S, Cerbu S, Dima CN, Borozan F, Pârvănescu R, Ilaș DG, Cîtu C, Vernic C, Sas I. AI in 2D Mammography: Improving Breast Cancer Screening Accuracy. Medicina. 2025;61(5):809. DOI: 10.3390/medicina61050809. [DOI:10.3390/medicina61050809] [PMID] []
27. Zeng A, Houssami N, Noguchi N, Nickel B, Marinovich ML. Frequency and characteristics of errors by artificial intelligence (AI) in reading screening mammography: a systematic review. Breast cancer research and treatment. 2024;207(1):1-3. DOI: 10.1007/s10549-024-07353-3. [DOI:10.1007/s10549-024-07353-3] [PMID] []
28. Park J, Witowski J, Xu Y, Trivedi H, Gichoya J, Brown-Mulry B, Westerhoff M, Moy L, Heacock L, Lewin A, Geras KJ. A Multi-Modal AI System for Screening Mammography: Integrating 2D and 3D Imaging to Improve Breast Cancer Detection in a Prospective Clinical Study. arXiv preprint arXiv:2504.05636. 2025. DOI: 10.48550/arXiv.2504.05636.
29. Rao KS, Terlapu PV, Jayaram D, Raju KK, Kumar GK, Pemula R. Intelligent ultrasound imaging for enhanced breast cancer diagnosis: ensemble transfer learning strategies. IEEE Access 2024 [DOI:10.1109/ACCESS.2024.3358448]
30. 12: 22243-63 [Internet]. 2024. DOI:10.1109/ACCESS.2024.3358448. [DOI:10.1109/ACCESS.2024.3358448]
31. Ghazalnaz Sharifonnasabi F, Makhdoom I. Comparison of Deep Learning and Machine Learning Algorithms to Diagnose and Predict Breast Cancer. In International Conference on Information Technology and Applications 2022(pp 31-43). Singapore: Springer Nature Singapore. DOI:10.1007/978-981-99-8324-7_4 [DOI:10.1007/978-981-99-8324-7_4]
32. Batool A, Byun YC. Toward improving breast cancer classification using an adaptive voting ensemble learning algorithm. IEEE Access. 2024;12:12869-82. DOI: 10.1109/ACCESS.2024.3356602 [DOI:10.1109/ACCESS.2024.3356602]
33. Xu M, Huang J, Huang K, Liu F. Incorporating tumor edge information for fine-grained bi-rads classification of breast ultrasound images. IEEE Access. 2024;12:38732-44. DOI: 10.1109/ACCESS.2024.3374380 [DOI:10.1109/ACCESS.2024.3374380]
34. Hamed G, Marey M, Amin SE, Tolba MF. Automated breast cancer detection and classification in full field digital mammograms using two full and cropped detection paths approach. IEEE Access. 2021;9:116898-913. DOI: 10.1109/ACCESS.2021.3105924. [DOI:10.1109/ACCESS.2021.3105924]
35. Ji Z, Sun H, Yuan N, Zhang H, Sheng J, Zhang X, Ganchev I. BGRD-TransUNet: A novel TransUNet-based model for ultrasound breast lesion segmentation. IEEE Access. 2024;12:31182-96. DOI: 10.1109/ACCESS.2024.3368170. [DOI:10.1109/ACCESS.2024.3368170]
36. Sutjiadi R, Sendari S, Herwanto HW, Kristian Y. Deep learning for segmentation and classification in mammograms for breast cancer detection: a systematic literature review. Advanced Ultrasound in Diagnosis and Therapy. 2024;8(3):94-105. DOI: 10.37015/AUDT.2024.230051 [DOI:10.37015/AUDT.2024.230051]
37. Mayo RC, Kent D, Sen LC, Kapoor M, Leung JW, Watanabe AT. Reduction of false-positive markings on mammograms: a retrospective comparison study using an artificial intelligence-based CAD. Journal of digital imaging. 2019;32(4):618-24. DOI: 10.1007/s10278-018-0168-6. [DOI:10.1007/s10278-018-0168-6] [PMID] []
38. Park J, Witowski J, Xu Y, Trivedi H, Gichoya J, Brown-Mulry B, Westerhoff M, Moy L, Heacock L, Lewin A, Geras KJ. A Multi-Modal AI System for Screening Mammography: Integrating 2D and 3D Imaging to Improve Breast Cancer Detection in a Prospective Clinical Study. arXiv preprint arXiv:2504.05636. 2025. DOI: 10.48550/arXiv.2504.05636.
39. Lotter W, Diab AR, Haslam B, Kim JG,Grisot G, Wu E, Wu K, Onieva JO, Boyer Y, Boxerman JL, Wang M. Robust breast cancer detection in mammography and digital breast tomosynthesis using an annotation-efficient deep learning approach. Nature medicine. 2021 Feb;27(2):244-9. DOI: 10.1038/s41591-020-01174-9. [DOI:10.1038/s41591-020-01174-9] [PMID] []
40. Parhizkari M, Shabanzadeh M, Abbasi F, Saremi S. A comprehensive review on breast cancer detection and using machine learning techniques: Methods, and challenges ahead. Advances in Applied Nano-Bio Technologies. 2025:24-45. DOI: 10.18502/aanbt.v6i1.18227 [DOI:10.18502/aanbt.v6i1.18227]
41. Pedemonte S, Tsue T, Mombourquette B, Vu YN, Matthews T, Hoil RM, Shah M, Ghare N, Zingman-Daniels N, Holley S, Appleton CM. A deep learning algorithm for reducing false positives in screening mammography. arXiv preprint arXiv:2204.06671. 2022. DOI: 10.1148/ryai.230033. [DOI:10.1148/ryai.230033] [PMID] []
42. Luo L, Wang X, Lin Y, Ma X, Tan A, Chan R, Vardhanabhuti V, Chu WC, Cheng KT, Chen H. Deep learning in breast cancer imaging: A decade of progress and future directions. IEEE Reviews in Biomedical Engineering. 2024. DOI: 10.1109/RBME.2024.3357877. [DOI:10.1109/RBME.2024.3357877] [PMID]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
