A.K. Al-Zubaidi1
1 Bunin Yelets State University (Yelets, Russia)

1 azhrstar90@gmail.com

The article focuses on developing an intelligent model for segmenting breast tumors in ultrasound images using the U-Net neural network architecture. The research emphasizes the importance of early cancer diagnosis and the role of artificial intelligence in improving healthcare quality. The developed model demonstrated high accuracy due to skip connections that preserve spatial details in the images. Despite its successes, the authors highlight areas for further improvement, such as incorporating attention mechanisms and expanding training datasets. The obtained results have practical significance for automated diagnostics and can be integrated into unified medical information systems, contributing to increased precision and efficiency in detecting cancerous lesions.

Al-Zubaidi A.K. Technique of intelligent segmentation of tumors on ultrasound images using the U-Net neural network architecture. Neurocomputers. 2025. V. 27. № 3. P. 26–32. DOI: https://doi.org/10.18127/j19998554-202503-04 (in Russian)

1. Golubeva T.S., Todua N.G., Belova E.V. Epidemiologiya i diagnostika raka molochnoj zhelezy na sovremennom etape. Universum: meditsina i farmakologiya. 2025. № 1 (118). S. 48–55. (in Russian)
2. Yap M.H., Pons G., Marti J. et al. Automated breast ultrasound lesions detection using convolutional neural networks. IEEE Journal of Biomedical and Health Informatics. 2017. V. 28. № 4. P. 1218–1226.
3. Morozova T.A., Smirnov I.V. Ul'trazvukovaya diagnostika opukholej molochnoj zhelezy. Ul'trazvuk v meditsine. 2022. T. 28. № 2. S. 56–62. (in Russian)
4. Litjens G., Kooi T., Bejnordi B.E. et al. A survey on deep learning in medical image analysis. Medical Image Analysis. 2017. V. 42. P. 60–88.
5. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional networks for biomedical image segmentation. MICCAI 2015. Lecture Notes in Computer Science. 2015. V. 9351. P. 234–241.
6. Islam M.R., Rahman M., Ali M. et al. Enhancing breast cancer segmentation and classification: An ensemble deep convolutional neural network and U-Net approach on ultrasound images. Machine Learning with Applications. 2024. V. 16. P. 100555. DOI: 10.1016/j.mlwa. 2024.100555.
7. Alzubaidi A.K., Petrov A.A. Ispol'zovanie vozmozhnostej modelej mashinnogo obucheniya EfficientNetB0 dlya analiza rentgenovskikh izobrazhenij pri diagnostike tuberkuleza. Nejrokomp'yutery: razrabotka, primenenie. 2024. T. 26 № 5. S. 41–48. DOI: 10.18127/ j19998554-202405-04. (in Russian)
8. Baza dannykh ul'trazvukovykh izobrazhenij molochnoj zhelezy (Breast ultrasound dataset) [Elektronnyj resurs]. URL: https://www.kaggle.com/ datasets/aryashah2k/breast-ultrasound-images-dataset (data obrashcheniya: 09.10.2024).
9. Al-Dhabyani W., Gomaa M., Khaled H., Fahmy A. Dataset of breast ultrasound images. Data in Brief. 2020. V. 28. P. 104863. DOI: 10.1016/j.dib.2019.104863.
10. Fedorov A.S., Dmitriev K.N. Ispol'zovanie svertochnykh nejronnykh setej dlya segmentatsii meditsinskikh izobrazhenij. Informatsionnye tekhnologii i vychislitel'nye sistemy. 2019. № 3. S. 45–53. (in Russian)
11. Zakharov V.A., Kuznetsova M.V. Avtomatizirovannaya segmentatsiya meditsinskikh izobrazhenij s ispol'zovaniem metodov glubokogo obucheniya. Vestnik komp'yuternoj grafiki i obrabotki izobrazhenij. 2021. T. 15. № 1. S. 20–30. (in Russian)
12. Yap M.H., Goyal M., Osman F.M., Martí R. et al. Breast ultrasound lesions recognition: A review. Medical Image Analysis. 2018. V. 36. P. 252–275.
13. Milletari F., Navab N., Ahmadi S.A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the 4th International Conference on 3D Vision (3DV). 2016. P. 565–571.
14. Oktay O., Schlemper J., Le Folgoc L., Lee M. et al. Attention U-Net: Learning where to look for the pancreas. arXiv preprint arXiv:1804. 03999. 2018.