UNISELF: A Unified Network with Instance Normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation

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/uponacceptance.

References in corpus (12)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Popular Ensemble Methods: An Empirical Study
• FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• Adaptive Diffusion Priors for Accelerated MRI Reconstruction
• Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation
• A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis
• DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation
• Boosting multiple sclerosis lesion segmentation through attention mechanism