Generalizable and Explainable Deep Learning for Medical Image Computing: An Overview
🤖 AI Summary
Clinical deployment of AI in medical imaging is hindered by poor generalizability across devices, institutions, and diseases, alongside insufficient interpretability and decision transparency.
Method: We propose the first unified framework that jointly integrates domain generalization and self-supervised pretraining—enhancing cross-domain robustness—with concept bottleneck models, disentangled attention, counterfactual reasoning, and uncertainty quantification—to improve decision interpretability and trustworthiness.
Contribution/Results: We systematically survey over 100 state-of-the-art works to clarify technical evolution and clinical translation bottlenecks. We introduce a novel, clinically grounded evaluation paradigm for trustworthy AI, spanning four orthogonal dimensions: performance, robustness, interpretability, and uncertainty. Our framework provides both a methodological foundation and a reproducible implementation roadmap for deploying reliable, clinically viable AI systems in medical imaging.
Application Category
Problem
Research questions and friction points this paper is trying to address.
Addressing transparency and explainability in medical AI applications.
Evaluating XAI techniques for improving model prediction transparency.
Enhancing robustness and generalizability of DL in biomedical imaging.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Combines ResNet50 with XAI for explainable results
Uses four CNNs across three medical datasets
Evaluates XAI techniques with confidence increase metric
🔎 Similar Papers
No similar papers found.
