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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gao, Yibo, Zhou, Hangqi, Gao, Zheyao, Wang, Bomin, Gao, Shangqi, Wang, Sihan, Zhuang, Xiahai
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916783746711552
author Gao, Yibo
Zhou, Hangqi
Gao, Zheyao
Wang, Bomin
Gao, Shangqi
Wang, Sihan
Zhuang, Xiahai
author_facet Gao, Yibo
Zhou, Hangqi
Gao, Zheyao
Wang, Bomin
Gao, Shangqi
Wang, Sihan
Zhuang, Xiahai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification
Gao, Yibo
Zhou, Hangqi
Gao, Zheyao
Wang, Bomin
Gao, Shangqi
Wang, Sihan
Zhuang, Xiahai
Computer Vision and Pattern Recognition
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.
title Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.14049