Structural Graph Neural Networks with Anatomical Priors for Explainable Chest X-ray Diagnosis

TL;DR

This paper introduces a graph neural network framework that incorporates anatomical priors for explainable chest X-ray diagnosis, enabling structured inference and intrinsic interpretability without post-hoc methods.

Contribution

It proposes a novel structural graph reasoning model with explicit spatial relations and anatomical priors for improved explainability in medical imaging diagnosis.

Findings

Enhanced interpretability through node importance scores

Improved diagnostic accuracy in chest X-ray analysis

Domain-agnostic framework for structured reasoning

Abstract

We present a structural graph reasoning framework that incorporates explicit anatomical priors for explainable vision-based diagnosis. Convolutional feature maps are reinterpreted as patch-level graphs, where nodes encode both appearance and spatial coordinates, and edges reflect local structural adjacency. Unlike conventional graph neural networks that rely on generic message passing, we introduce a custom structural propagation mechanism that explicitly models relative spatial relations as part of the reasoning process. This design enables the graph to act as an inductive bias for structured inference rather than a passive relational representation. The proposed model jointly supports node-level lesion-aware predictions and graph-level diagnostic reasoning, yielding intrinsic explainability through learned node importance scores without relying on post-hoc visualization techniques. We demonstrate the approach through a chest X-ray case study, illustrating how structural priors guide relational reasoning and improve interpretability. While evaluated in a medical imaging context, the framework is domain-agnostic and aligns with the broader vision of graph-based reasoning across artificial intelligence systems. This work contributes to the growing body of research exploring graphs as computational substrates for structure-aware and explainable learning.