FGML-DG: Feynman-Inspired Cognitive Science Paradigm for Cross-Domain Medical Image Segmentation

TL;DR

This paper introduces a novel cognitive science-inspired meta-learning framework, FGML-DG, for improving cross-domain medical image segmentation by mimicking human learning processes to enhance knowledge transfer and model robustness.

Contribution

It is the first to incorporate Feynman-inspired cognitive principles into meta-learning for medical image domain generalization, addressing style feature simplification and feedback-driven optimization.

Findings

Outperforms existing methods on two medical image domain generalization tasks.

Effectively simplifies complex style features for better domain alignment.

Enhances model adaptability through feedback-driven re-training strategy.

Abstract

In medical image segmentation across multiple modalities (e.g., MRI, CT, etc.) and heterogeneous data sources (e.g., different hospitals and devices), Domain Generalization (DG) remains a critical challenge in AI-driven healthcare. This challenge primarily arises from domain shifts, imaging variations, and patient diversity, which often lead to degraded model performance in unseen domains. To address these limitations, we identify key issues in existing methods, including insufficient simplification of complex style features, inadequate reuse of domain knowledge, and a lack of feedback-driven optimization. To tackle these problems, inspired by Feynman's learning techniques in educational psychology, this paper introduces a cognitive science-inspired meta-learning paradigm for medical image domain generalization segmentation. We propose, for the first time, a cognitive-inspired Feynman-Guided Meta-Learning framework for medical image domain generalization segmentation (FGML-DG), which mimics human cognitive learning processes to enhance model learning and knowledge transfer. Specifically, we first leverage the 'concept understanding' principle from Feynman's learning method to simplify complex features across domains into style information statistics, achieving precise style feature alignment. Second, we design a meta-style memory and recall method (MetaStyle) to emulate the human memory system's utilization of past knowledge. Finally, we incorporate a Feedback-Driven Re-Training strategy (FDRT), which mimics Feynman's emphasis on targeted relearning, enabling the model to dynamically adjust learning focus based on prediction errors. Experimental results demonstrate that our method outperforms other existing domain generalization approaches on two challenging medical image domain generalization tasks.