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

arXiv: https://arxiv.org/abs/2508.03982 · HTML: https://mlsanity.com/paper/2508.03982/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 102 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 30 of 41)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning](https://mlsanity.com/paper/2003.04696/) (2020)
- [The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation](https://mlsanity.com/paper/1611.09326/) (2016)
- [Adaptive Diffusion Priors for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2207.05876/) (2022)
- [FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline](https://mlsanity.com/paper/1910.03866/) (2019)
- [Time-Dependent Deep Image Prior for Dynamic MRI](https://mlsanity.com/paper/1910.01684/) (2019)
- [On the Effect of Inter-observer Variability for a Reliable Estimation of Uncertainty of Medical Image Segmentation](https://mlsanity.com/paper/1806.02562/) (2018)
- [Shifts 2.0: Extending The Dataset of Real Distributional Shifts](https://mlsanity.com/paper/2206.15407/) (2022)
- [ModDrop++: A Dynamic Filter Network with Intra-subject Co-training for Multiple Sclerosis Lesion Segmentation with Missing Modalities](https://mlsanity.com/paper/2203.04959/) (2022)
- [One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks](https://mlsanity.com/paper/1805.12415/) (2018)
- [Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach](https://mlsanity.com/paper/1702.04869/) (2017)
- [HACA3: A Unified Approach for Multi-site MR Image Harmonization](https://mlsanity.com/paper/2212.06065/) (2022)
- [A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis](https://mlsanity.com/paper/2005.05135/) (2020)
- [Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation](https://mlsanity.com/paper/1811.02942/) (2018)
- [Fidelity Imposed Network Edit (FINE) for Solving Ill-Posed Image Reconstruction](https://mlsanity.com/paper/1905.07284/) (2019)
- [DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation](https://mlsanity.com/paper/2012.07950/) (2020)
- [Quantifying white matter hyperintensity and brain volumes in heterogeneous clinical and low-field portable MRI](https://mlsanity.com/paper/2312.05119/) (2023)
- [Scanner Invariant Multiple Sclerosis Lesion Segmentation from MRI](https://mlsanity.com/paper/1910.10035/) (2019)
- [Disentangling A Single MR Modality](https://mlsanity.com/paper/2205.04982/) (2022)
- [Multiple Sclerosis Lesion Analysis in Brain Magnetic Resonance Images: Techniques and Clinical Applications](https://mlsanity.com/paper/2104.10029/) (2021)
- [RSANet: Recurrent Slice-wise Attention Network for Multiple Sclerosis Lesion Segmentation](https://mlsanity.com/paper/2002.12470/) (2020)
- [Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation](https://mlsanity.com/paper/2009.05576/) (2020)

## Built on by (most cited first, 2 of 2)

- [Encoder-Only Image Registration](https://mlsanity.com/paper/2509.00451/) (2025)
- [MSRepaint: Multiple Sclerosis Repaint with Conditional Denoising Diffusion Implicit Model for Bidirectional Lesion Filling and Synthesis](https://mlsanity.com/paper/2510.02063/) (2025)

## Abstract (arXiv)

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.