Guideline-Aware XAI for Imaging: Closing the Trust Gap in Clinical AI

View at publisher Summarise with VIRAT
Authors: Krishna Karan Ghantasala
Cited by: 0
References: 21

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper interrogates explainable AI practices in medical imaging through a dual lens: how XAI is used to justify model decisions and how often studies align with healthcare reporting standards that enable trustworthy adoption in clinics. Using a structured literature rubric (2020-2025) and a PubMed-based citation analysis of frameworks (TRIPOD/CLAIM/TRIPOD-AI/DECIDE-AI/FUTURE-AI), the study finds single-digit uptake for recent guidelines and persistent reliance on older checklists, despite widespread deployment claims, highlighting a transparencyadoption paradox in radiology AI. The synthesis maps common XAI techniques (saliency, attribution, attention, perturbation) to clinical validation stages and identifies systemic barriers-low awareness, weak enforcement, and checklist complexity-while outlining actionable levers for healthcare XAI: human-centered explanation design, prospective evaluation with standardized reports, and automated compliance tooling to make explanations auditable and clinically reliable.

Fields of Study & Subjects

Explainable Artificial Intelligence (XAI) Artificial Intelligence in Healthcare and Education Radiomics and Machine Learning in Medical Imaging

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
2124–2130
Publication date
21 January 2026
Language
EN