Interpretable fundus image-based glaucoma classification using aCDR-guided vascular tortuosity analysis

This study aimed to develop and evaluate an interpretable hierarchical auxiliary classification framework for glaucoma-related fundus image analysis, with emphasis on transparent classification rationale for cases with intermediate aCDR values.

A MiT-B2-scSE U-Net was employed to jointly segment the optic disc and optic cup from fundus images, and the aCDR was calculated for initial image-level classification. Samples within predefined low- and high-aCDR ranges were directly classified, whereas samples in the intermediate-aCDR group underwent further analysis using peripapillary vessel segmentation and skeleton-based tortuosity quantification. To improve the reliability of vascular morphology assessment, a distance-aware topology-constrained loss function (DATCL) was introduced in the vessel segmentation stage to improve the segmentation accuracy of peripapillary vessels and improve the reliability of subsequent calculations.

On the current REFUGE-based test set, the proposed MiT-B2-scSE U-Net achieved a mean Dice similarity coefficient (Dice) of 0.9254 and a mean Intersection over Union (IoU) of 0.8694 for joint optic cup-disc segmentation. For image-level glaucoma classification, the hierarchical aCDR-plus-vessel strategy achieved an accuracy of 91.25%, compared with 85.0% for the aCDR-only baseline and 66.25% for the vessel-only strategy.

The proposed framework suggests that combining optic cup-disc morphology with local vascular tortuosity may provide complementary information for interpretable glaucoma classification in fundus images with intermediate aCDR values. It provides a methodological avenue for deep learning-assisted glaucoma screening.

The online version contains supplementary material available at https://doi.org/10.1007/s13755-026-00484-5.