Diabetic Retinopathy Lesion Segmentation through Attention Mechanisms
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917256590524416 |
|---|---|
| author | Jithesh, Aruna Karumuri, Chinmayi Kotha, Venkata Kiran Reddy Doddapuneni, Meghana Jeong, Taehee |
| author_facet | Jithesh, Aruna Karumuri, Chinmayi Kotha, Venkata Kiran Reddy Doddapuneni, Meghana Jeong, Taehee |
| contents | Diabetic Retinopathy (DR) is an eye disease which arises due to diabetes mellitus. It might cause vision loss and blindness. To prevent irreversible vision loss, early detection through systematic screening is crucial. Although researchers have developed numerous automated deep learning-based algorithms for DR screening, their clinical applicability remains limited, particularly in lesion segmentation. Our method provides pixel-level annotations for lesions, which practically supports Ophthalmologist to screen DR from fundus images. In this work, we segmented four types of DR-related lesions: microaneurysms, soft exudates, hard exudates, and hemorrhages on 757 images from DDR dataset. To enhance lesion segmentation, an attention mechanism was integrated with DeepLab-V3+. Compared to the baseline model, the Attention-DeepLab model increases mean average precision (mAP) from 0.3010 to 0.3326 and the mean Intersection over Union (IoU) from 0.1791 to 0.1928. The model also increased microaneurysm detection from 0.0205 to 0.0763, a clinically significant improvement. The detection of microaneurysms is the earliest visible symptom of DR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07301 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Diabetic Retinopathy Lesion Segmentation through Attention Mechanisms Jithesh, Aruna Karumuri, Chinmayi Kotha, Venkata Kiran Reddy Doddapuneni, Meghana Jeong, Taehee Computer Vision and Pattern Recognition Diabetic Retinopathy (DR) is an eye disease which arises due to diabetes mellitus. It might cause vision loss and blindness. To prevent irreversible vision loss, early detection through systematic screening is crucial. Although researchers have developed numerous automated deep learning-based algorithms for DR screening, their clinical applicability remains limited, particularly in lesion segmentation. Our method provides pixel-level annotations for lesions, which practically supports Ophthalmologist to screen DR from fundus images. In this work, we segmented four types of DR-related lesions: microaneurysms, soft exudates, hard exudates, and hemorrhages on 757 images from DDR dataset. To enhance lesion segmentation, an attention mechanism was integrated with DeepLab-V3+. Compared to the baseline model, the Attention-DeepLab model increases mean average precision (mAP) from 0.3010 to 0.3326 and the mean Intersection over Union (IoU) from 0.1791 to 0.1928. The model also increased microaneurysm detection from 0.0205 to 0.0763, a clinically significant improvement. The detection of microaneurysms is the earliest visible symptom of DR. |
| title | Diabetic Retinopathy Lesion Segmentation through Attention Mechanisms |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.07301 |