Decoupling Predictions in Distributed Learning for Multi-Center Left Atrial MRI Segmentation

TL;DR

This paper introduces a novel distributed learning framework for multi-center left atrial MRI segmentation that decouples predictions to enhance performance on both generic and local data, addressing data heterogeneity issues.

Contribution

It proposes a new method that bridges global and personalized approaches by decoupling predictions through distribution-conditioned adaptation matrices.

Findings

Outperforms existing methods on multi-center LA MRI segmentation

Improves accuracy for both generic and local data

Demonstrates robustness across different data distributions

Abstract

Distributed learning has shown great potential in medical image analysis. It allows to use multi-center training data with privacy protection. However, data distributions in local centers can vary from each other due to different imaging vendors, and annotation protocols. Such variation degrades the performance of learning-based methods. To mitigate the influence, two groups of methods have been proposed for different aims, i.e., the global methods and the personalized methods. The former are aimed to improve the performance of a single global model for all test data from unseen centers (known as generic data); while the latter target multiple models for each center (denoted as local data). However, little has been researched to achieve both goals simultaneously. In this work, we propose a new framework of distributed learning that bridges the gap between two groups, and improves the performance for both generic and local data. Specifically, our method decouples the predictions for generic data and local data, via distribution-conditioned adaptation matrices. Results on multi-center left atrial (LA) MRI segmentation showed that our method demonstrated superior performance over existing methods on both generic and local data. Our code is available at https://github.com/key1589745/decouple_predict