Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification

TL;DR

This paper introduces CRL, a framework that learns logical rules from binarized visual concepts to improve interpretability and generalizability in medical image classification, addressing concept leakage and global decision logic.

Contribution

CRL is a novel method that learns Boolean logical rules from concepts, capturing correlations for better interpretability and out-of-distribution generalization in medical imaging.

Findings

CRL achieves competitive accuracy with existing methods.

CRL significantly improves out-of-distribution generalization.

CRL provides both local and global interpretability.

Abstract

The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended information within soft concept representations undermines both interpretability and generalizability. Moreover, most concept-based models focus solely on local explanations (instance-level), neglecting the global decision logic (dataset-level). To address these limitations, we propose Concept Rule Learner (CRL), a novel framework to learn Boolean logical rules from binarized visual concepts. CRL employs logical layers to capture concept correlations and extract clinically meaningful rules, thereby providing both local and global interpretability. Experiments on two medical image classification tasks show that CRL achieves competitive performance with existing methods while significantly improving generalizability to out-of-distribution data. The code of our work is available at https://github.com/obiyoag/crl.