WRCANet: wavelet residual cross-attention network for meibomian gland segmentation
Abstract
To address challenges in automatic meibomian gland segmentation for meibomian gland dysfunction (MGD) diagnosis, such as size variation and blurred edges, this study proposes a wavelet residual cross-attention network (WRCANet). The network utilizes wavelet residual blocks to preserve boundary details and a cross-attention-based global feature aggregation module to handle varying gland sizes. Evaluated on both in-house and public datasets, WRCANet achieves Dice scores of 90.20% and 84.60% respectively, outperforming other state-of-the-art methods. By effectively enhancing gland boundary discrimination, the model shows significant potential for precise morphological analysis and auxiliary clinical diagnosis of MGD.
Fields of Study & Subjects
Medical Image Segmentation Techniques
Retinal Imaging and Analysis
Ocular Surface and Contact Lens
Publication details
- Journal / source
- Biomedical Optics Express
- Volume
- 17
- Issue
- 4
- Pages
- 1595–1595
- Publication date
- 16 February 2026
- Language
- EN