Federated Self-supervised Domain Generalization for Label-efficient Polyp Segmentation

TL;DR

This paper introduces LFDG, a federated self-supervised domain generalization approach that improves polyp segmentation across diverse medical centers by enhancing data diversity and stability in feature learning.

Contribution

LFDG combines adversarial data augmentation and a relaxation module to enhance federated model generalization for label-efficient polyp segmentation.

Findings

Achieves 3.80% better than baseline in performance.

Outperforms recent FL and SSL methods by 3.92%.

Validated on six medical centers' data.

Abstract

Employing self-supervised learning (SSL) methodologies assumes par-amount significance in handling unlabeled polyp datasets when building deep learning-based automatic polyp segmentation models. However, the intricate privacy dynamics surrounding medical data often preclude seamless data sharing among disparate medical centers. Federated learning (FL) emerges as a formidable solution to this privacy conundrum, yet within the realm of FL, optimizing model generalization stands as a pressing imperative. Robust generalization capabilities are imperative to ensure the model's efficacy across diverse geographical domains post-training on localized client datasets. In this paper, a Federated self-supervised Domain Generalization method is proposed to enhance the generalization capacity of federated and Label-efficient intestinal polyp segmentation, named LFDG. Based on a classical SSL method, DropPos, LFDG proposes an adversarial learning-based data augmentation method (SSADA) to enhance the data diversity. LFDG further proposes a relaxation module based on Source-reconstruction and Augmentation-masking (SRAM) to maintain stability in feature learning. We have validated LFDG on polyp images from six medical centers. The performance of our method achieves 3.80% and 3.92% better than the baseline and other recent FL methods and SSL methods, respectively.