Explainable Artificial Intelligence in Biomedical Image Analysis: A Comprehensive Survey

TL;DR

This comprehensive survey reviews explainable AI methods in biomedical image analysis, emphasizing modality-specific approaches, recent multimodal and vision-language advances, and practical evaluation tools to enhance transparency and trust.

Contribution

It provides a structured, modality-aware taxonomy of XAI techniques, explores emerging multimodal and vision-language paradigms, and offers practical guidance and critical analysis for future research.

Findings

Categorized XAI methods by principles, strengths, and limitations.

Highlighted the importance of modality-specific interpretability challenges.

Reviewed evaluation metrics and open-source frameworks for XAI in biomedical imaging.

Abstract

Explainable artificial intelligence (XAI) has become increasingly important in biomedical image analysis to promote transparency, trust, and clinical adoption of DL models. While several surveys have reviewed XAI techniques, they often lack a modality-aware perspective, overlook recent advances in multimodal and vision-language paradigms, and provide limited practical guidance. This survey addresses this gap through a comprehensive and structured synthesis of XAI methods tailored to biomedical image analysis.We systematically categorize XAI methods, analyzing their underlying principles, strengths, and limitations within biomedical contexts. A modality-centered taxonomy is proposed to align XAI methods with specific imaging types, highlighting the distinct interpretability challenges across modalities. We further examine the emerging role of multimodal learning and vision-language models in explainable biomedical AI, a topic largely underexplored in previous work. Our contributions also include a summary of widely used evaluation metrics and open-source frameworks, along with a critical discussion of persistent challenges and future directions. This survey offers a timely and in-depth foundation for advancing interpretable DL in biomedical image analysis.