MIRNet: Integrating Constrained Graph-Based Reasoning with Pre-training for Diagnostic Medical Imaging
This addresses annotation scarcity and label imbalance in diagnostic medical imaging, particularly for tongue analysis, though it is incremental as it combines existing techniques like MAE and GAT.
The paper tackled automated interpretation of medical images by introducing MIRNet, which integrates self-supervised pre-training with constrained graph-based reasoning, achieving state-of-the-art performance on a new large dataset for tongue diagnosis.
Automated interpretation of medical images demands robust modeling of complex visual-semantic relationships while addressing annotation scarcity, label imbalance, and clinical plausibility constraints. We introduce MIRNet (Medical Image Reasoner Network), a novel framework that integrates self-supervised pre-training with constrained graph-based reasoning. Tongue image diagnosis is a particularly challenging domain that requires fine-grained visual and semantic understanding. Our approach leverages self-supervised masked autoencoder (MAE) to learn transferable visual representations from unlabeled data; employs graph attention networks (GAT) to model label correlations through expert-defined structured graphs; enforces clinical priors via constraint-aware optimization using KL divergence and regularization losses; and mitigates imbalance using asymmetric loss (ASL) and boosting ensembles. To address annotation scarcity, we also introduce TongueAtlas-4K, a comprehensive expert-curated benchmark comprising 4,000 images annotated with 22 diagnostic labels--representing the largest public dataset in tongue analysis. Validation shows our method achieves state-of-the-art performance. While optimized for tongue diagnosis, the framework readily generalizes to broader diagnostic medical imaging tasks.