Graph-Augmented Topological Internalization with Dual-Stream Classifiers for Medical Report Generation

TL;DR

This paper introduces GDMRG, a novel framework for medical report generation that incorporates topological disease knowledge and dual-stream classifiers to improve diagnostic accuracy and interpretability.

Contribution

The work proposes a graph-augmented, topologically aware model with dual classifiers and a diagnosis-guided attention mechanism, enhancing reasoning and handling imbalanced data in medical report generation.

Findings

Achieves competitive clinical efficacy on MIMIC-CXR dataset.

Demonstrates robust zero-shot generalization on IU X-Ray dataset.

Effectively incorporates disease co-occurrence priors without external retrieval.

Abstract

Automated medical report generation, MRG, holds substantial value for alleviating radiologist workload and enhancing diagnostic efficiency. However, mainstream approaches typically treat diverse chest abnormalities as isolated classification targets. This paradigm often overlooks inherent disease co-occurrences and struggles to translate medical topological structures into explicit data correlations, constraining the model's reasoning capacity on complex or subtle lesions. To address this, we propose a Graph-Augmented Dual-Stream Medical Report Generation with Topological Internalization, GDMRG. Our framework introduces a Topological Knowledge Internalization module, TKI, which leverages a Graph Convolutional Network, GCN, to generate an explicit parameterized weight matrix based on global disease co-occurrence priors. This facilitates efficient topological knowledge injection without relying on external retrieval mechanisms. Building upon this, we construct a dual-stream classification system: the main branch generates discrete diagnostic prompts under topological constraints, while the auxiliary branch employs an asymmetric optimization strategy to dynamically calibrate decision boundaries for highly imbalanced samples. Concurrently, to establish a logical closed loop between diagnosis and visual grounding, we design a diagnostic-driven Diagnosis-Guided Spatial Attention, DGSA, that utilizes high-dimensional clinical semantics to recalibrate the visual encoder, mitigating feature hallucinations. Comprehensive experiments on the MIMIC-CXR dataset demonstrate that GDMRG achieves competitive clinical efficacy, CE, while maintaining natural language fluency. Furthermore, our model exhibits robust zero-shot generalization on the IU X-Ray dataset. In summary, this work presents an integrated and interpretable paradigm for medical report generation.