AI RESEARCH
Fundus Image-based Glaucoma Screening via Retinal Knowledge-Oriented Dynamic Multi-Level Feature Integration
arXiv CS.CV
•
ArXi:2604.12351v1 Announce Type: new Automated diagnosis based on color fundus photography is essential for large-scale glaucoma screening. However, existing deep learning models are typically data-driven and lack explicit integration of retinal anatomical knowledge, which limits their robustness across heterogeneous clinical datasets. Moreover, pathological cues in fundus images may appear beyond predefined anatomical regions, making fixed-region feature extraction insufficient for reliable diagnosis.