# UNISELF: A unified network with instance normalization and self-ensembled lesion fusion for multiple sclerosis lesion segmentation

## TL;DR

UNISELF is a new deep learning method for segmenting multiple sclerosis lesions in MRI scans that works well even when data sources differ.

## Contribution

UNISELF introduces self-ensembled lesion fusion and test-time instance normalization to improve accuracy and generalization in MS lesion segmentation.

## Key findings

- UNISELF achieves top performance on the ISBI 2015 test dataset.
- It outperforms existing methods on out-of-domain datasets with domain shifts and missing contrasts.
- The method is robust to variations in acquisition protocols and imaging artifacts.

## Abstract

Automated segmentation of multiple sclerosis (MS) lesions using multicontrast magnetic resonance (MR) images improves efficiency and reproducibility compared to manual delineation, with deep learning (DL) methods achieving state-of-the-art performance. However, these DL-based methods have yet to simultaneously optimize in-domain accuracy and out-of-domain generalization when trained on a single source with limited data, or their performance has been unsatisfactory. To fill this gap, we propose a method called UNISELF, which achieves high accuracy within a single training domain while demonstrating strong generalizability across multiple out-of-domain test datasets. UNISELF employs a novel test-time self-ensembled lesion fusion to improve segmentation accuracy, and leverages test-time instance normalization (TTIN) of latent features to address domain shifts and missing input contrasts. Trained on the ISBI 2015 longitudinal MS segmentation challenge training dataset, UNISELF ranks among the best-performing methods on the challenge test dataset. Additionally, UNISELF outperforms all benchmark methods trained on the same ISBI training data across diverse out-of-domain test datasets with domain shifts and missing contrasts, including the public MICCAI 2016 and UMCL datasets, as well as a private multisite dataset. These test datasets exhibit domain shifts and/or missing contrasts caused by variations in acquisition protocols, scanner types, and imaging artifacts arising from imperfect acquisition. Our code is available at https://github.com/Jinwei1209/UNISELF.