Instance-level quantitative saliency in multiple sclerosis lesion segmentation.

ABSTRACT: In recent years, explainable methods for artificial intelligence (XAI) have tried to reveal and describe models' decision mechanisms in the case of classification and even for segmentation. However, XAI methods for semantic segmentation and in particular for single specific instances (e.g. one given lesion among others of the same class in medical imaging) have yet to be developed to understand what drove the detection and contouring of the latter, which is crucial for all multi-lesional diseases. We proposed instance-level explanation maps for semantic segmentation extending both SmoothGrad and Grad-CAM++ methods and yielding quantitative instance saliency for the former. The instance-level methods were applied to the segmentation of white matter lesions (WML), a magnetic resonance imagin

SUBMITTER: Spagnolo F 

PROVIDER: S-EPMC12916819 | biostudies-literature | 2026 Feb

REPOSITORIES: biostudies-literature