# Fundus Image-based Glaucoma Screening via Retinal Knowledge-Oriented Dynamic Multi-Level Feature Integration

arXiv: https://arxiv.org/abs/2604.12351 · HTML: https://mlsanity.com/paper/2604.12351/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 45 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation](https://mlsanity.com/paper/1801.00926/) (2018)
- [AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge](https://mlsanity.com/paper/2302.01738/) (2023)
- [G1020: A Benchmark Retinal Fundus Image Dataset for Computer-Aided Glaucoma Detection](https://mlsanity.com/paper/2006.09158/) (2020)
- [Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluation](https://mlsanity.com/paper/2202.01069/) (2022)
- [Label uncertainty-guided multi-stream model for disease screening](https://mlsanity.com/paper/2201.12089/) (2022)
- [Enhancing Fundus Image-based Glaucoma Screening via Dynamic Global-Local Feature Integration](https://mlsanity.com/paper/2504.00431/) (2025)

## Abstract (arXiv)

While deep learning has advanced automated glaucoma screening via color fundus photography, existing purely data-driven models often overfit to confounding imaging artifacts and struggle to capture unpredictable pathological cues located beyond predefined anatomical boundaries. To address these limitations, we propose a retinal knowledge-oriented framework that synergizes dynamic multi-scale feature learning with domain-specific anatomical priors. The proposed architecture adopts a tri-branch structure to jointly model the global retinal context, the structural characteristics of the optic cup and disc, and dynamically cropped pathological regions. Specifically, we devise a Dynamic Window Mechanism (DWM) that adaptively discovers diagnostically informative patches via image-level supervision. Furthermore, we introduce a Knowledge-Enhanced Convolutional Block Attention Module (KE-CBAM) that explicitly incorporates retinal priors from a pre-trained foundation model RETFound to guide spatial attention, preventing the network from assigning spurious weights to irrelevant background noise. Extensive evaluations on the large-scale AIROGS dataset demonstrate that our method achieves a state-of-the-art AUC of 98.5% and an accuracy of 94.6%. More importantly, the integration of anatomical priors effectively mitigates the inherent class imbalance, significantly improving the detection of referable glaucoma cases. Additional validations on the SMDG-19 benchmark further confirm its superior cross-domain generalization, indicating that our contribution provides a robust, interpretable, and scalable solution for real-world clinical glaucoma diagnosis. Our code is available at https://github.com/magiczhuo/Glaucoma-Detection