Scanner Invariant Multiple Sclerosis Lesion Segmentation from MRI

TL;DR

This paper introduces a novel MRI segmentation method that enhances generalization across different scanning sites by integrating a regularization network with an auxiliary loss, effectively reducing domain shifts.

Contribution

The paper presents a new domain-invariant segmentation approach combining a traditional encoder-decoder with a regularization network and auxiliary loss.

Findings

Outperforms baseline models in multi-site MS lesion segmentation

Improves generalization across diverse MRI scanning sites

Validated on a large clinical dataset with 117 patients from 56 sites

Abstract

This paper presents a simple and effective generalization method for magnetic resonance imaging (MRI) segmentation when data is collected from multiple MRI scanning sites and as a consequence is affected by (site-)domain shifts. We propose to integrate a traditional encoder-decoder network with a regularization network. This added network includes an auxiliary loss term which is responsible for the reduction of the domain shift problem and for the resulting improved generalization. The proposed method was evaluated on multiple sclerosis lesion segmentation from MRI data. We tested the proposed model on an in-house clinical dataset including 117 patients from 56 different scanning sites. In the experiments, our method showed better generalization performance than other baseline networks.