Explainable Artificial Intelligence (XAI) in Computational Pathology: Definitions, Taxonomy, and Recommendations
Artificial IntelligenceComputer Vision and Pattern Recognition
Summary
The authors review how explainable AI (XAI) techniques are used in computational pathology, which applies AI to analyze medical images for diagnosis and treatment. They create a clear set of terms and categories to organize the many different XAI methods, helping to make sense of how these tools work and when to use them. The authors also connect specific clinical questions to the best-suited explainability methods and highlight key challenges that currently limit clinical use. They suggest practical steps to improve trust and safety in AI-assisted pathology.
Authors
Shubham Innani, Suhang You, Adam Shephard, Bhakti Baheti, Francesco Ciompi, Joe Yeong, Nasir Rajpoot, Michael Feldman, Solene Florence Kammerer-Jacquet, Dimitrios Makris, Geert Litjens, Anne L. Martel, Jana Lipkova, April Khademi, Spyridon Bakas, for the MICCAI SIG-CompPath
Abstract
Computational pathology (CompPath) is transforming medicine by leveraging artificial intelligence (AI) algorithms to support diagnosis, prognosis, and treatment prediction from gigapixel whole-slide images. Clinical adoption is progressing, but is constrained by concerns about safety, accountability, and regulatory oversight in high-stakes clinical environments. Explainable AI (XAI) systems hold promise for building trust and enabling verification, yet the literature remains fragmented due to inconsistent terminology, overlapping methodological families, ad hoc validation, and current reviews. This review aims to formalize XAI methods in CompPath through the: i) introduction of a pathology-centric vocabulary comprising seven core terms; ii) development of a taxonomy across methodological families and three orthogonal axes (stage, type, scope); and iii) establishment of a task-driven framework that maps five clinical questions to recommended methods, method evaluation, and deployment context. Five key gaps between current XAI capabilities and clinical deployment are identified, and actionable steps are proposed to advance XAI for CompPath.