An adaptive multi-label classification model for diabetic retinopathy lesion recognition.
10.7507/1001-5515.202503056
- Author:
Xina LIU
1
;
Jun XIE
2
;
Junjun HOU
3
;
Xinying XU
1
;
Yan GUO
4
Author Information
1. College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, P. R. China.
2. College of Electronic Information and Optical Engineering, Taiyuan University of Technology, Jinzhong, Shanxi 030600, P. R. China.
3. Shanxi Eye Hospital, Taiyuan 030002, P. R. China.
4. The Third Affiliated Hospital of Beijing University of Chinese Medicine, Beijing 100084, P. R. China.
- Publication Type:Journal Article
- Keywords:
Category-adaptive mapping;
Diabetic retinopathy;
Fundus fluorescein angiography;
Label-specific decoding;
Lesion recognition;
Multi-label classification;
Smooth focal loss
- MeSH:
Diabetic Retinopathy/diagnostic imaging*;
Humans;
Fluorescein Angiography;
Microaneurysm/diagnostic imaging*;
Retinal Vessels;
Algorithms
- From:
Journal of Biomedical Engineering
2025;42(5):892-900
- CountryChina
- Language:Chinese
-
Abstract:
Diabetic retinopathy is a common blinding complication in diabetic patients. Compared with conventional fundus color photography, fundus fluorescein angiography can dynamically display retinal vessel permeability changes, offering unique advantages in detecting early small lesions such as microaneurysms. However, existing intelligent diagnostic research on diabetic retinopathy images primarily focuses on fundus color photography, with relatively insufficient research on complex lesion recognition in fluorescein angiography images. This study proposed an adaptive multi-label classification model (D-LAM) to improve the recognition accuracy of small lesions by constructing a category-adaptive mapping module, a label-specific decoding module, and an innovative loss function. Experimental results on a self-built dataset demonstrated that the model achieved a mean average precision of 96.27%, a category F1-score of 91.21%, and an overall F1-score of 94.58%, with particularly outstanding performance in recognizing small lesions such as microaneurysms (AP = 1.00), significantly outperforming existing methods. The research provides reliable technical support for clinical diagnosis of diabetic retinopathy based on fluorescein angiography.
