|
Аннотация.
Работа посвящена проблеме выявления на ранней стадии рака молочной железы с применением гибридных подходов, сочетающих свёрточные нейронные сети (CNN) с методами машинного обучения на основе радиомики. Новая гибридная архитектура объединяет ResNet50 с модулем CBAM, трансформер-блок внимания, радиомные дескрипторы. Эксперименты на CBIS-DDSM (accuracy = 99.4%, AUC = 99.98%) и валидация на INbreast (AUC = 97.6%). Её применение подтверждают высокую точность и устойчивость. Анализ Grad-CAM++ демонстрирует интерпретируемость, обеспечивая клиническую применимость предложенного подхода для CADx систем ранней диагностики.
Ключевые слова:
рак молочной железы, микрокальцификаты, ResNet50, ViT, CBAM, радиомика, CBIS-DDSM.
DOI 10.14357/20718632260207
EDN ITRPCQ
Стр. 66-76.
Литература
1. Alsajer H. Classification of Microcalcifications in Breast Cancer Using Hybrid Deep Learning Techniques, and Image Analysis // In Computer Science On-line Conference. 2025. Vol. 2. P. 160-171. 2. Aly G.H., Marey M., El-Sayed S.A., Tolba M.F. YOLO based breast masses detection and classification in full-field digital mammograms // Computer methods and programs in biomedicine. 2021. Vol. 200. P.105823. 3. Thakur, A., Gupta, M., Sinha, D.K., Mishra, K.K., Venkatesan, V.K. and Guluwadi, S. Transformative breast Cancer diagnosis using CNNs with optimized ReduceLROnPlateau and Early stopping // Enhancements International Journal of Computational Intelligence Systems. 2024. Vol. 17. No. 1.P. 14. 4. Ayana G., Dese K., Dereje Y., Kebede Y., Barki H., Amdissa D., Husen N., Mulugeta F., Habtamu B., Choe S.W. Vision-transformer-based transfer learning for mammogram classification // Diagnostics. 2023. Vol. 13. No. 2. P.178. 5. Boudouh SS, Bouakkaz M. Advancing precision in breast cancer detection: a fusion of vision transformers and CNNs for calcification mammography classification: SS Boudouh and M. Bouakkaz // Applied Intelligence. 2024. Vol. 54. No. 17. P. 8170-8183. 6. Chakraborty R., Bairagi A., Samui P., Das S. Noise removal from digital mammogram // European Journal of Pharmaceutical and Medical Research. 2019. Vol. 6. P. 312-319. 7. Chen X., Zhang K., Abdoli N., Gilley P.W., Wang X., Liu H., Zheng B., Qiu Y. Transformers improve breast cancer diagnosis from unregistered multi-view mammograms // Diagnostics. 2022. Vol. 12. No. 7. P. 1549. 8. Ciecholewski M. Malignant and benign mass segmentation in mammograms using active contour methods // Symmetry. 2017. Vol. 9. No. 11. P. 277. 9. Debelee T.G., Schwenker F., Ibenthal A., Yohannes D. Survey of deep learning in breast cancer image analysis // Evolving Systems. 2020. Vol. 11. No. 1. P. 143-63. 10. Dhungel N, Carneiro G, Bradley AP. Automated mass detection in mammograms using cascaded deep learning and random forests // In2015 international conference on digital image computing: techniques and applications (DICTA). 2015. Vol. 23. P. 1-8. 11. Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J. An image is worth 16x16 words: Transformers for image recognition at scale // arXiv preprint arXiv:2010.11929. 2020. 12. Hassan N.M., Hamad S., Mahar K. Mammogram breast cancer CAD systems for mass detection and classification: a review // Multimedia Tools and Applications. 2022. Vol. 81. No. 14. P. 20043-20075. 13. Igbokwe K.K. Comparative examination of breast cancer burden in sub-Saharan Africa, 1990–2019: estimates from Global Burden of Disease 2019 study // BMJ open. 2024. Vol. 14. No. 3. P. e082492. 14. Jiménez-Gaona Y., Rodríguez-Álvarez M.J., Lakshminarayanan V. Deep-learning-based computer-aided systems for breast cancer imaging: a critical review // Applied Sciences. 2020. Vol. 10. No. 22. P. 8298. 15. Kim S., Tran T.X., Song H., Park B. Microcalcifications, mammographic breast density, and risk of breast cancer: a cohort study // Breast Cancer Research. 2022. Vol. 24. No. 1. P. 96. 16. Lee R.S., Gimenez F., Hoogi A., Miyake K.K., Gorovoy M., Rubin D.L. A curated mammography data set for use in computer-aided detection and diagnosis research // Scientific data. 2017. Vol. 4. No. 1. P. 170177. 17. Loizidou K., Elia R., Pitris C. Computer-aided breast cancer detection and classification in mammography: A comprehensive review // Computers in Biology and Medicine. 2023. Vol. 153. P. 106554. 18. Marasinou C., Li B., Paige J., Omigbodun A., Nakhaei N., Hoyt A., Hsu W. Improving the Quantitative Analysis of Breast Microcalcifications: A Multiscale Approach Journal of Digital Imaging. 2023. Vol. 36(3). P. 1016-28. 19. Mehta S, Singh M. Assessing the Efficacy of CNN-SVM Hybrids in Breast Tumor Recognition. In2024 2nd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS) 2024. P. 138-142. 20. Mendes J., Matela N. Breast cancer risk assessment: a review on mammography-based approaches // Journal of Imaging. 2021. Vol. 7. No. 6. P.98. 21. Moreira I.C., Amaral I., Domingues I., Cardoso A., Cardoso M.J., Cardoso J.S. Inbreast: toward a full-field digital mammographic database // Academic radiology. 2012. Vol. 19. No. 2. P. 236-48. 22. Mosquera C., Ferrer L., Milone D.H., Luna D., Ferrante E. Class imbalance on medical image classification: towards better evaluation practices for discrimination and calibration performance // European Radiology. 2024. Vol. 34. No. 12. P. 7895-7903. 23. Nemade V., Pathak S., Dubey A.K. A systematic literature review of breast cancer diagnosis using machine intelligence techniques // Archives of Computational Methods in Engineering. 2022. Vol. 29. No. 6. P. 4401-4430. 24. Nissar I, Alam S, Masood S, Kashif M. MOB-CBAM: A dual-channel attention-based deep learning generalizable model for breast cancer molecular subtypes prediction using mammograms // Computer Methods and Programs in Biomedicine. 2024. Vol. 248. P. 108121. 25. Parekh V, Jacobs MA. Radiomics: a new application from established techniques // Expert review of precision medicine and drug development. 2016. Vol. 1. No. 2. P. 207-226. 26. Paul S., Batra S., Mohiuddin K., Miladi M.N., Anand D., A. Nasr O. A novel ensemble weight-assisted Yolov5-based deep learning technique for the localization and detection of malaria parasites // Electronics. 2022. Vol. 11. No. 23. P. 3999. 27. Pesapane F., Trentin C., Ferrari F., Signorelli G., Tantrige P., Montesano M., Cicala C., Virgoli R., D'Acquisto S., Nicosia L., Origgi D. Deep learning performance for detection and classification of microcalcifications on mammography // European radiology experimental. 2023. Vol. 7. No. 1. P. 69. 28. Prinzi F., Orlando A., Gaglio S., Vitabile S. Interpretable radiomic signature for breast microcalcification detection and classification // Journal of Imaging Informatics in Medicine. 2024. Vol. 37. No. 3. P. 1038-53. 29. Ramadan S.Z. Methods used in computer-aided diagnosis for breast cancer detection using mammograms: a review // Journal of healthcare engineering. 2020. Vol. 2020. No. 1. P. 9162464. 30. Salmi M., Atif D., Oliva D., Abraham A., Ventura S. Handling imbalanced medical datasets: review of a decade of research // Artificial intelligence review. 2024. Vol. 57. No. 10. P. 273. 31. Shah S.M., Khan R.A., Arif S., Sajid U. Artificial intelligence for breast cancer analysis: Trends & directions // Computers in Biology and Medicine. 2022. Vol. 142. P. 105221. 32. Shen L., Margolies L.R., Rothstein J.H., Fluder E., McBride R., Sieh W. Deep learning to improve breast cancer detection on screening mammography // Scientific reports. 2019. Vol. 9. No. 1. P. 12495. 33. Shorten C., Khoshgoftaar T.M. A survey on image data augmentation for deep learning // Journal of big data. 2019. Vol. 6. No. 1. P. 1-48. 34. Singh B.K., Sinha G.R., editors. Intelligent Computing Techniques in Biomedical Imaging: Methods, Case Studies, and Applications. Elsevier. 2024. P. 143. 35. Suckling J. The mammographic images analysis society digital mammogram database. InExpertia Medica // International Congress Series, 1994. Vol. 1994. No. 1069. P. 375-378. 36. Sung H., Ferlay J., Siegel R.L., Laversanne M., Soerjomataram I., Jemal A., Bray F. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries// CA: a cancer journal for clinicians. 2021. Vol. 71. No. 3. P. 209-249. 37. Karaca Aydemir B.K., Telatar Z., Güney S., Dengiz B. Detecting and classifying breast masses via YOLO-based deep learning // Neural Computing and Applications. 2025. Vol. 37. No. 17. P. 11555-11582. 38. Yadav S.S., Jadhav S.M. Deep convolutional neural network based medical image classification for disease diagnosis // Journal of Big data. 2019. Vol. 6. No. 1. P. 1-8. 39. Zahoor S., Lali I.U., Khan M.A., Javed K., Mehmood W. Breast cancer detection and classification using traditional computer vision techniques: a comprehensive review // Current Medical Imaging Reviews. 2020. Vol. 16. No. 10. P. 1187-1200. 40. Zuiderveld K. Contrast limited adaptive histogram equalization. In: Heckbert PS (ed.). Graphics Gems IV. San Diego: Academic Press Professional, Inc.; 1994. p. 474-485. doi: 10.1016/B978-0-12-336156-1.50061-6 41. Zwanenburg A., Leger S., Vallieres M., Lock S.. Image biomarker standardisation initiative // arXiv preprint arXiv:1612.07003. 2016.
|
