Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentation

2025-03-30

AI Summary

To address segmentation challenges in medical imaging federated learning—stemming from single-sample annotation, cross-modality (MR/CT) discrepancies, and cross-device heterogeneity—this paper proposes the first federated self-supervised single-shot segmentation framework. Methodologically, it pioneers the adaptation of self-supervised few-shot segmentation to federated settings, integrating contrastive pretraining, multimodal feature alignment, and an enhanced Dice loss. The framework enables collaborative training across heterogeneous modality clients without sharing raw data or labels. On unseen local validation sets, it matches or surpasses the performance of a FedAvg-based CoWPro variant, demonstrating superior generalization and robustness. Key contributions include: (1) establishing federated self-supervised single-shot segmentation as a novel research direction; (2) enabling effective cross-modal federated joint training; and (3) empirically validating the feasibility of multi-center medical image segmentation under ultra-low annotation budgets.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Distributed Machine Learning & Federated Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Decentralized federated learning enables learning of data representations from multiple sources without compromising the privacy of the clients. In applications like medical image segmentation, where obtaining a large annotated dataset from a single source is a distressing problem, federated self-supervised learning can provide some solace. In this work, we push the limits further by exploring a federated self-supervised one-shot segmentation task representing a more data-scarce scenario. We adopt a pre-existing self-supervised few-shot segmentation framework CoWPro and adapt it to the federated learning scenario. To the best of our knowledge, this work is the first to attempt a self-supervised few-shot segmentation task in the federated learning domain. Moreover, we consider the clients to be constituted of data from different modalities and imaging techniques like MR or CT, which makes the problem even harder. Additionally, we reinforce and improve the baseline CoWPro method using a fused dice loss which shows considerable improvement in performance over the baseline CoWPro. Finally, we evaluate this novel framework on a completely unseen held-out part of the local client dataset. We observe that the proposed framework can achieve performance at par or better than the FedAvg version of the CoWPro framework on the held-out validation dataset.

Problem

• Federated self-supervised one-shot segmentation for data-scarce scenarios
• Cross-modal and cross-imaging technique segmentation in federated learning
• Improving baseline CoWPro with fused dice loss for better performance

Innovation

• Federated self-supervised one-shot segmentation
• Adapted CoWPro for federated learning
• Fused dice loss improves baseline