# A Dual Edge Spatial Jacobian Image Graph for Interpretable Diabetic Retinopathy Grading

arXiv: https://arxiv.org/abs/2606.24168 · HTML: https://mlsanity.com/paper/2606.24168/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 10 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 1 of 1)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)

## Abstract (arXiv)

Automated diabetic retinopathy (DR) grading from colour fundus photographs can achieve strong predictive performance, but clinical interpretation requires more than an image-level label. It requires understanding how lesion evidence is distributed around retinal vessels and how this evidence relates to quantitative vascular biomarkers. We present a dual-edge spatial-Jacobian image graph for interpretable DR grading. Each fundus image is represented as a graph node with four aligned evidence streams: AutoMorph vessel information (X1), DR-XAI-style lesion evidence maps (X2), a 128-dimensional lesion-based contrastive image embedding (X3), and AutoMorph morphometric biomarkers (X4). The spatial edge branch (X12) encodes vessel-lesion geometry, while the Jacobian branch (X34) models embedding-biomarker sensitivity. Lightweight two-token attention fuses both edge families into a final image graph. On 2,910 matched non-augmented APTOS images, the full graph achieves 0.8076 accuracy, 0.8312 quadratic weighted kappa, 0.5915 macro-F1, and 0.9330 adjacent-grade accuracy; referable DR reaches 0.9055 accuracy and 0.9711 AUROC. The framework is positioned as an explainable representation-learning tool for lesion-biomarker hypothesis generation, rather than as a deployment-ready clinical classifier. The code is available at https://github.com/Inamullah-Colab/dual-edge-dr-graph-xai.