| dc.contributor.author | Himbitskaya, E. | |
| dc.contributor.author | Svistunova, K. | |
| dc.contributor.author | Kezik, S. | |
| dc.date.accessioned | 2026-05-15T08:43:36Z | |
| dc.date.available | 2026-05-15T08:43:36Z | |
| dc.date.issued | 2025 | |
| dc.identifier.uri | https://rep.bsmu.by/handle/BSMU/60511 | |
| dc.description | Himbitskaya, E. Segmentation-Based Attention Mask for Enhancing Fundus Image Diagnosing / E. Himbitskaya, K. Svistunova, S. Kezik // Pattern Recognition and Information Processing (PRIP'2025) : Proc. of the 17th Int. Conf., Minsk, Belarus, 16–18 Sept. 2025 / United Institute of Informatics Problems of the National Academy of Sciences of Belarus ; ed.: A. Tuzikov, A. Belotserkovsky. – Minsk, 2025. – P. 443–445. – URL: https://prip.by/2025/assets/files/PRIP2025_Proceedings_final.pdf. | ru_RU |
| dc.description.abstract | Abstract. Approach to improve the classification of ocular diseases from fundus images by leveraging semantic segmentation as an attention mechanism. Key anatomical structures – optic disc, optic cup, and retinal vessels – are segmented using deep learning models and combined into weighted attention masks. These masks guide a classifier based on EfficientNetB6 to focus on clinically relevant regions, resulting in significant improvements in diagnostic accuracy. The method enhances detection sensitivity for subtle disease features and increases model interpretability. | ru_RU |
| dc.language.iso | ru | ru_RU |
| dc.title | Segmentation-Based Attention Mask for Enhancing Fundus Image Diagnosing | ru_RU |
| dc.type | Article | ru_RU |
