RobustEMD: Domain Robust Matching for Cross-domain Few-shot Medical Image Segmentation

2024-10-01

arXiv.org

AI Summary

To address the poor generalization of few-shot medical image segmentation (FSMIS) models across domains—e.g., across hospitals, imaging devices, and modalities (MRI/T2/CT)—this paper proposes a domain-robust few-shot segmentation framework. Methodologically, it introduces: (i) the first Earth Mover’s Distance (EMD)-based point-set-level domain matching mechanism to align feature distributions; (ii) a Sobel gradient-weighted strategy that suppresses domain-specific feature nodes and enhances robust foreground support-query feature alignment; and (iii) a unified few-shot semantic segmentation paradigm applicable across modalities, acquisition sequences, and institutions. Evaluated on eight datasets spanning three anatomical regions under three major cross-domain settings, the framework consistently outperforms state-of-the-art methods, achieving new SOTA performance.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Few-shot medical image segmentation (FSMIS) aims to perform the limited annotated data learning in the medical image analysis scope. Despite the progress has been achieved, current FSMIS models are all trained and deployed on the same data domain, as is not consistent with the clinical reality that medical imaging data is always across different data domains (e.g. imaging modalities, institutions and equipment sequences). How to enhance the FSMIS models to generalize well across the different specific medical imaging domains? In this paper, we focus on the matching mechanism of the few-shot semantic segmentation models and introduce an Earth Mover's Distance (EMD) calculation based domain robust matching mechanism for the cross-domain scenario. Specifically, we formulate the EMD transportation process between the foreground support-query features, the texture structure aware weights generation method, which proposes to perform the sobel based image gradient calculation over the nodes, is introduced in the EMD matching flow to restrain the domain relevant nodes. Besides, the point set level distance measurement metric is introduced to calculated the cost for the transportation from support set nodes to query set nodes. To evaluate the performance of our model, we conduct experiments on three scenarios (i.e., cross-modal, cross-sequence and cross-institution), which includes eight medical datasets and involves three body regions, and the results demonstrate that our model achieves the SoTA performance against the compared models.

Problem

• Few-shot Segmentation
• Medical Imaging
• Domain Adaptation

Innovation

• RobustEMD
• Earth Mover's Distance
• Few-shot Medical Image Segmentation