AGE-Net: Spectral--Spatial Fusion and Anatomical Graph Reasoning with Evidential Ordinal Regression for Knee Osteoarthritis Grading

2026-01-24

AI Summary

This study addresses the challenges in automated Kellgren–Lawrence (KL) grading of knee osteoarthritis, which arise from subtle structural changes, long-range anatomical dependencies, and ambiguous boundaries between adjacent grades. To tackle these issues, the authors propose AGE-Net, a novel framework that uniquely integrates spectral-spatial features (SSF), anatomical graph reasoning (AGR), and evidence-based ordinal regression grounded in the Normal-Inverse-Gamma distribution. AGE-Net further incorporates a differential refinement module and pairwise ranking constraints to model prediction uncertainty while preserving ordinal consistency. Built upon a ConvNeXt backbone, the model achieves a quadratic weighted kappa (QWK) of 0.9017 ± 0.0045 and mean squared error (MSE) of 0.2349 ± 0.0028 on the KL dataset, significantly outperforming state-of-the-art CNN-based methods. Ablation studies confirm the effectiveness and robustness of each component within the proposed architecture.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Graph-based Machine Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Automated Kellgren--Lawrence (KL) grading from knee radiographs is challenging due to subtle structural changes, long-range anatomical dependencies, and ambiguity near grade boundaries. We propose AGE-Net, a ConvNeXt-based framework that integrates Spectral--Spatial Fusion (SSF), Anatomical Graph Reasoning (AGR), and Differential Refinement (DFR). To capture predictive uncertainty and preserve label ordinality, AGE-Net employs a Normal-Inverse-Gamma (NIG) evidential regression head and a pairwise ordinal ranking constraint. On a knee KL dataset, AGE-Net achieves a quadratic weighted kappa (QWK) of 0.9017 +/- 0.0045 and a mean squared error (MSE) of 0.2349 +/- 0.0028 over three random seeds, outperforming strong CNN baselines and showing consistent gains in ablation studies. We further outline evaluations of uncertainty quality, robustness, and explainability, with additional experimental figures to be included in the full manuscript.

Problem

• Knee Osteoarthritis Grading
• Kellgren–Lawrence Grading
• Radiographic Assessment
• Ordinal Classification
• Anatomical Dependencies

Innovation

• Spectral-Spatial Fusion
• Anatomical Graph Reasoning
• Evidential Ordinal Regression
• Normal-Inverse-Gamma
• Knee Osteoarthritis Grading