Cover
Vol. 2 No. 2 (2026)

Published: October 7, 2026

Pages: 139 - 148

Original Article

A Multi-Layer Clinical Decision Support Framework for Mammographic Breast Lesion Detection, Radiomics-Based Characterization, and BI-RADS-Oriented Assessment

Hadeel Abdul-Majeed Ghazi 1 Yarub Alazzawi 2 Hussein Hasan Nsaif 3
1 Department of Mechatronics Engineering, Al-Khwarizmi College of Engineering, University of Baghdad, Baghdad, Iraq.
2 Department of Mechatronics Engineering, Al-Khwarizmi College of Engineering, University of Baghdad, Baghdad, Iraq
3 Radiology Department, Oncology Teaching Hospital, Medical City Complex, Baghdad, Iraq.
History
  • Received: August 24, 2026
  • Revised: September 18, 2026
  • Accepted: November 3, 2026
  • Available Online: November 14, 2026
DOI

https://doi.org/10.33971/ijmrai.2.2.5

Abstract

Breast cancer is one of the leading causes of mortality among women worldwide and necessitates an accurate and clinically valid mammographic assessment. Although recent deep learning frameworks have achieved promising performance in breast lesion detection, many existing frameworks focus primarily on lesion localization without providing comprehensive decision-support functionalities for clinical practice. In this study, a multi-layer clinical decision support framework is developed for mammographic breast lesion assessment by integrating YOLOv8x-based detection, ROI-based quantitative image descriptors, ROI/contour-derived geometric descriptors, physician-selected Breast Imaging Reporting and Data System (BI-RADS) assessment with associated risk visualization, and physician-editable structured report generation, all within a single workflow. The framework was developed and evaluated using 501 mammographic images. The dataset was divided into 350 training, 100 validations, and 51 test images. In the standard curve-based evaluation, the detector achieved 99.50% mAP@50 and 99.16% mAP@50-95. At the fixed confidence operating point of 0.40, the detector achieved 97.87% precision, 100.00% recall and a 98.92% F1-score. The platform extends beyond automated detection into quantitative ROI analysis, physician-editable reporting, automated PDF generation, and clinician-supervised mammographic decision support. The system does not perform autonomous diagnosis or automatic BI-RADS assignment.

Keywords

References

  1. C. R. Taylor, N. Monga, C. Johnson, J. R. Hawley, and M. Patel, “Artificial Intelligence Applications in Breast Imaging: Current Status and Future Directions,” Diagnostics, vol. 13, no. 12, Art. no. 2041, 2023, doi: 10.3390/diagnostics13122041.
  2. N. Ferreira, A. Peres, C. Rennó-Costa, and R. C. Moioli, “Pre-Processing Pipeline and Imaging Equipment Impact the Performance of CNN for Breast Cancer Detection in Mammograms: Evidence from CBIS-DDSM and VinDr-Mammo,” IEEE Access, vol. 14, pp. 75198-75208, 2026, doi: 10.1109/ACCESS.2026.3693553.
  3. F. J. Gilbert and K. Pinker-Domenig, “Diagnosis and Staging of Breast Cancer: When and How to Use Mammography, Tomosynthesis, Ultrasound, Contrast-Enhanced Mammography, and Magnetic Resonance Imaging,” in Diseases of the Chest, Breast, Heart and Vessels 2019-2022. Cham: Springer, pp. 155-166, 2019, doi: 10.1007/978-3-030-11149-6_13.
  4. F. Hoseini and M. Kheyri, “A hybrid Capsule Network-based computer-aided diagnosis framework for breast cancer detection in mammographic images,” Intelligence-Based Medicine, vol. 14, Art. no. 100381, 2026, doi: 10.1016/j.ibmed.2026.100381.
  5. J. Li and Z. Jiang, “Artificial intelligence in breast cancer: applications and advancements,” Cancer Biology & Medicine, vol. 23, no. 3, pp. 363-373, 2026, doi: 10.20892/j.issn.2095-3941.2025.0704.
  6. B. Arabov, A. Razaque, G. Kairedenova, and M. A. Khan, “Hybrid Approach for Breast Cancer Detection Using CNNs and Real-Time Risk Assessment,” in 2025 1st International Conference on Secure IoT, Assured and Trusted Computing (SATC), IEEE, pp. 1-6, 2025, doi: 10.1109/SATC65530.2025.11137232.
  7. D. C. Lepcha, B. Goyal, A. Dogra, A. Alkhayyat, P. K. Sahu, A. Ali, and V. Kukreja, “Deep Learning in Medical Image Analysis: A Comprehensive Review of Algorithms, Trends, Applications, and Challenges,” Computer Modeling in Engineering & Sciences, vol. 145, no. 2, pp. 1487-1573, 2025, doi: 10.32604/cmes.2025.070964.
  8. F. Prinzi, M. Insalaco, A. Orlando, S. Gaglio, and S. Vitabile, “A Yolo-Based Model for Breast Cancer Detection in Mammograms,” Cognitive Computation, vol. 16, pp. 107-120, 2024, doi: 10.1007/s12559-023-10189-6.
  9. B. K. Karaca Aydemir, Z. Telatar, S. Güney, and B. Dengiz, “Detecting and classifying breast masses via YOLO-based deep learning,” Neural Computing and Applications, vol. 37, pp. 11555-11582, 2025, doi: 10.1007/s00521-025-11153-1.
  10. S. Wang, Z. Xu, B. Zheng, H. Zeng, D. Pan, M. Ma, W. Chen, and G. Qin, “Improvement in matching lesions in dual-view mammograms using a geometric model,” BMC Medical Imaging, vol. 25, no. 1, Art. no. 322, 2025, doi: 10.1186/s12880-025-01862-3.
  11. S. R. Kebede, F. G. Waldamichael, T. G. Debelee, M. Aleme, W. Bedane, B. Mezgebu, and Z. C. Merga, “Dual view deep learning for enhanced breast cancer screening using mammography,” Scientific Reports, vol. 14, Art. no. 3839, 2024, doi: 10.1038/s41598-023-50797-8.
  12. N. Shifa, M. Saleh, Y. Akbari, and S. Al Maadeed, “A review of explainable AI techniques and their evaluation in mammography for breast cancer screening,” Clinical Imaging, vol. 123, Art. no. 110492, 2025, doi: 10.1016/j.clinimag.2025.110492.
  13. A. Ciardiello, A. D’Angelo, L. De Angelis, S. Giagu, E. Sala, and G. Gigante, “Beyond the black box: lessons in explainability from AI in mammography,” Artificial Intelligence Review, vol. 59, Art. no. 130, 2026, doi: 10.1007/s10462-026-11518-5.
  14. Y.-J. Qi, G.-H. Su, C. You, X. Zhang, Y. Xiao, Y.-Z. Jiang, and Z.-M. Shao, “Radiomics in breast cancer: Current advances and future directions,” Cell Reports Medicine, vol. 5, no. 9, Art. no. 101719, 2024, doi: 10.1016/j.xcrm.2024.101719.
  15. A. Shiwlani, A. Ahmad, M. Umar, N. Dharejo, A. Tahir, and S. Shiwlani, “BI-RADS Category Prediction from Mammography Images and Mammography Radiology Reports Using Deep Learning: A Systematic Review,” Jurnal Ilmiah Computer Science, vol. 3, no. 1, pp. 30-49, 2024, doi: 10.58602/jics.v3i1.31.
  16. X. Lu, Y. Jia, H. Zhang, R. Wu, W. Zhao, Z. Yao, F. Nie, and Y. Ma, “Deep learning-based and BI-RADS guided radiomics model for tumour-infiltrating lymphocytes evaluation in breast cancer,” British Journal of Radiology, Art. no. tqae129, 2024, doi: 10.1093/bjr/tqae129.
  17. D. Bhati, F. Neha, and M. Amiruzzaman, “A Survey on Explainable Artificial Intelligence (XAI) Techniques for Visualizing Deep Learning Models in Medical Imaging,” Journal of Imaging, vol. 10, no. 10, Art. no. 239, 2024, doi: 10.3390/jimaging10100239.
  18. H. T. Nguyen, H. Q. Nguyen, H. H. Pham, K. Lam, L. T. Le, M. Dao, and V. Vu, “VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography,” Scientific Data, vol. 10, no. 1, Art. no. 277, 2023, doi: 10.1038/s41597-023-02100-7.
  19. J. J. Jeong, B. L. Vey, A. Bhimireddy, T. Kim, T. Santos, R. Correa, R. Dutt, M. Mosunjac, G. Oprea-Ilies, G. Smith, M. Woo, C. R. McAdams, M. S. Newell, I. Banerjee, J. Gichoya, and H. Trivedi, “The EMory BrEast Imaging Dataset (EMBED): A Racially Diverse, Granular Dataset of 3.4 Million Screening and Diagnostic Mammographic Images,” Radiology: Artificial Intelligence, vol. 5, no. 1, Art. no. e220047, 2023, doi: 10.1148/ryai.220047.
  20. B. Abdikenov, D. Rakishev, Y. Orazayev, and T. Zhaksylyk, “Enhancing Breast Lesion Detection in Mammograms via Transfer Learning,” Journal of Imaging, vol. 11, no. 9, Art. no. 314, 2025, doi: 10.3390/jimaging11090314.
  21. G. Wang, D. Shi, Q. Guo, H. Zhang, S. Wang, and K. Ren, “Radiomics Based on Digital Mammography Helps to Identify Mammographic Masses Suspicious for Cancer,” Frontiers in Oncology, vol. 12, Art. no. 843436, 2022, doi: 10.3389/fonc.2022.843436.
  22. G. Yao, L. Chen, T. Wu, Y. Liu, Y. Wan, Z. Xia, B. Liu, and M. Zheng, “Mammography Based Nomogram Integrating Radiomics and Clinical Features to Predict Benign or Malignant Regression of BI-RADS 4A Lesions at Follow-Up,” International Journal of Women’s Health, vol. 17, pp. 3097-3106, 2025, doi: 10.2147/IJWH.S539131.
  23. J. W. Seo, Y. J. Kim, and K. G. Kim, “Leveraging paired mammogram views with deep learning for comprehensive breast cancer detection,” Scientific Reports, vol. 15, Art. no. 4406, 2025, doi: 10.1038/s41598-025-88907-3.
  24. B. Abdikenov, T. Zhaksylyk, A. Imasheva, Y. Orazayev, and T. Karibekov, “Innovative Multi-View Strategies for AI-Assisted Breast Cancer Detection in Mammography,” Journal of Imaging, vol. 11, no. 8, Art. no. 247, 2025, doi: 10.3390/jimaging11080247.
  25. F. Manigrasso, R. Milazzo, A. S. Russo, F. Lamberti, F. Strand, A. Pagnani, and L. Morra, “Mammography classification with multi-view deep learning techniques: Investigating graph and transformer-based architectures,” Medical Image Analysis, vol. 99, Art. no. 103320, 2025, doi: 10.1016/j.media.2024.103320.
  26. F. Pesapane, A. Rotili, S. Penco, V. Dominelli, F. Priolo, I. Marinucci, L. Nicosia, R. Grasso, G. Pravettoni, and E. Cassano, “Explainable Artificial Intelligence in Mammography: A Systematic Review of Methods, Evaluation Practices, and Clinical Readiness,” Diagnostics, vol. 16, no. 9, Art. no. 1412, 2026, doi: 10.3390/diagnostics16091412.
  27. H. A. M. Ghazi, Y. Alazzawi, and H. H. Nsaif, “A YOLOv8x Framework for Breast Lesion Localization Using Real-World Mammographic Images,” Karbala International Journal of Modern Science, vol. 12, no. 4, pp. 1-13, 2026, doi: 10.33640/2405-609X.3487.