Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.09256 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929713714298880 |
|---|---|
| author | Li, Zesheng Liao, Minwen Chen, Haoran Su, Yan Pan, Chengchang Qi, Honggang |
| author_facet | Li, Zesheng Liao, Minwen Chen, Haoran Su, Yan Pan, Chengchang Qi, Honggang |
| contents | The hemorrhagic lesion segmentation plays a critical role in ophthalmic diagnosis, directly influencing early disease detection, treatment planning, and therapeutic efficacy evaluation. However, the task faces significant challenges due to lesion morphological variability, indistinct boundaries, and low contrast with background tissues. To improve diagnostic accuracy and treatment outcomes, developing advanced segmentation techniques remains imperative. This paper proposes an adversarial learning-based dynamic architecture adjustment approach that integrates hierarchical U-shaped encoder-decoder, residual blocks, attention mechanisms, and ASPP modules. By dynamically optimizing feature fusion, our method enhances segmentation performance. Experimental results demonstrate a Dice coefficient of 0.6802, IoU of 0.5602, Recall of 0.766, Precision of 0.6525, and Accuracy of 0.9955, effectively addressing the challenges in fundus image hemorrhage segmentation.[* Corresponding author.] |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09256 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DynSegNet:Dynamic Architecture Adjustment for Adversarial Learning in Segmenting Hemorrhagic Lesions from Fundus Images Li, Zesheng Liao, Minwen Chen, Haoran Su, Yan Pan, Chengchang Qi, Honggang Computer Vision and Pattern Recognition Artificial Intelligence The hemorrhagic lesion segmentation plays a critical role in ophthalmic diagnosis, directly influencing early disease detection, treatment planning, and therapeutic efficacy evaluation. However, the task faces significant challenges due to lesion morphological variability, indistinct boundaries, and low contrast with background tissues. To improve diagnostic accuracy and treatment outcomes, developing advanced segmentation techniques remains imperative. This paper proposes an adversarial learning-based dynamic architecture adjustment approach that integrates hierarchical U-shaped encoder-decoder, residual blocks, attention mechanisms, and ASPP modules. By dynamically optimizing feature fusion, our method enhances segmentation performance. Experimental results demonstrate a Dice coefficient of 0.6802, IoU of 0.5602, Recall of 0.766, Precision of 0.6525, and Accuracy of 0.9955, effectively addressing the challenges in fundus image hemorrhage segmentation.[* Corresponding author.] |
| title | DynSegNet:Dynamic Architecture Adjustment for Adversarial Learning in Segmenting Hemorrhagic Lesions from Fundus Images |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.09256 |