GlaKG: A Biomarker-Centric Fundus Knowledge Graph for Explainable Glaucoma Diagnosis and Risk Assessment
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors created GlaKG, a tool to help diagnose glaucoma by combining eye images with known medical rules and biomarkers. Instead of just giving a diagnosis, GlaKG explains the reasoning behind it by showing which biomarkers and rules it used. They tested it on a public eye image dataset and got very high accuracy, but they note the dataset's biomarkers are closely linked to labels, so results represent an ideal case rather than purely image-based performance. Their work focuses on making glaucoma diagnosis more transparent and understandable for doctors.
GlaucomaFundus ImageBiomarkersKnowledge GraphResNet50Risk StratificationClinical InterpretabilityImage EmbeddingsFeature ImportancePost-processing Fusion
Authors
Cheng Huang, Jia Zhang, Yi Jiang, Yang Liu, Karanjit Kooner, Yadi Liu, Tsengdar Lee, Yang Xie, Wenqi Shi, Guanghua Xiao
Abstract
Glaucoma is a leading cause of irreversible blindness worldwide, yet most automated diagnosis systems rely on opaque deep-learning models that offer little clinical interpretability. We present GlaKG, a biomarker-centric fundus knowledge graph that integrates structural biomarkers, clinically grounded rules, and image features to produce traceable reasoning for glaucoma diagnosis and risk stratification. GlaKG encodes six entity types (Fundus Image, Optic Disc, Neural Rim, Pathology, Diagnosis, Risk Level), eight relation types, and 11 clinically validated rules into a unified graph, so that every prediction is accompanied by an explicit reasoning chain linking biomarker evidence to activated clinical rules. To keep knowledge-based reasoning strictly separate from label information, we adopt a post-processing fusion framework that combines ResNet50 image embeddings with a normalized KG reasoning-chain score via a tunable weight alpha, with all fitting confined to the training split. On a publicly available, AI-annotated fundus dataset, GlaKG reaches F1 = 0.9953 for binary glaucoma classification and 0.930 accuracy with 0.922 weighted F1 for four-class risk stratification; we report openly that the dataset's biomarker annotations are highly label-correlated, and therefore frame these figures as an upper bound attainable with clean structured biomarkers rather than as leakage-free image-only performance. Feature-importance analysis shows KG-derived and biomarker features contributing near-equally (51.1% vs. 48.9%), and the reasoning chain flags borderline cases by exposing low chain scores rather than failing silently. GlaKG's central contribution is therefore a clinically auditable reasoning framework that complements raw predictive performance by explicitly exposing the biomarker evidence and rule activations behind each decision.