Towards Multi-dimensional Explanation Alignment for Medical Classification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hu, Lijie, Lai, Songning, Chen, Wenshuo, Xiao, Hongru, Lin, Hongbin, Yu, Lu, Zhang, Jingfeng, Wang, Di
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908105554526208
author Hu, Lijie
Lai, Songning
Chen, Wenshuo
Xiao, Hongru
Lin, Hongbin
Yu, Lu
Zhang, Jingfeng
Wang, Di
author_facet Hu, Lijie
Lai, Songning
Chen, Wenshuo
Xiao, Hongru
Lin, Hongbin
Yu, Lu
Zhang, Jingfeng
Wang, Di
contents The lack of interpretability in the field of medical image analysis has significant ethical and legal implications. Existing interpretable methods in this domain encounter several challenges, including dependency on specific models, difficulties in understanding and visualization, as well as issues related to efficiency. To address these limitations, we propose a novel framework called Med-MICN (Medical Multi-dimensional Interpretable Concept Network). Med-MICN provides interpretability alignment for various angles, including neural symbolic reasoning, concept semantics, and saliency maps, which are superior to current interpretable methods. Its advantages include high prediction accuracy, interpretability across multiple dimensions, and automation through an end-to-end concept labeling process that reduces the need for extensive human training effort when working with new datasets. To demonstrate the effectiveness and interpretability of Med-MICN, we apply it to four benchmark datasets and compare it with baselines. The results clearly demonstrate the superior performance and interpretability of our Med-MICN.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21494
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Multi-dimensional Explanation Alignment for Medical Classification
Hu, Lijie
Lai, Songning
Chen, Wenshuo
Xiao, Hongru
Lin, Hongbin
Yu, Lu
Zhang, Jingfeng
Wang, Di
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
The lack of interpretability in the field of medical image analysis has significant ethical and legal implications. Existing interpretable methods in this domain encounter several challenges, including dependency on specific models, difficulties in understanding and visualization, as well as issues related to efficiency. To address these limitations, we propose a novel framework called Med-MICN (Medical Multi-dimensional Interpretable Concept Network). Med-MICN provides interpretability alignment for various angles, including neural symbolic reasoning, concept semantics, and saliency maps, which are superior to current interpretable methods. Its advantages include high prediction accuracy, interpretability across multiple dimensions, and automation through an end-to-end concept labeling process that reduces the need for extensive human training effort when working with new datasets. To demonstrate the effectiveness and interpretability of Med-MICN, we apply it to four benchmark datasets and compare it with baselines. The results clearly demonstrate the superior performance and interpretability of our Med-MICN.
title Towards Multi-dimensional Explanation Alignment for Medical Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.21494