Backend
SWIMSS: An Open Multi-Center SwinUNETR Model for Multiple Sclerosis White Matter Lesion Segmentation
arXiv eess.IV0 views
arXiv:2611.23351v1 Announce Type: new Abstract: Purpose: To develop and validate SWIMSS (SWInUNETR for Multiple Sclerosis white matter lesion Segmentation), a SwinUNETR-based deep learning (DL) model for reliable automated white matter (WM) lesion segmentation, in a large multicentric cohort of people with multiple sclerosis (pwMS). Methods: A real-world longitudinal dataset of 1,385 pwMS from seven Swiss clinical centers was used to train, validate, and test SWIMSS and two state-of-the-art DL architectures: UNETR and MSSegDiff. Inference results obtained with LST-AI were also compared. Preprocessed magnetization-prepared rapid acquisition gradient echo and fluid-attenuated inversion recovery MRI sequences, acquired with various MR systems and field strengths, served as model inputs. Model performance was evaluated using the Dice similarity coefficient (DSC) with 95% confidence intervals (CI). Results: SWIMSS achieved the highest performance, with a DSC of 81.37 (95% CI: 80.63-82.11), outperforming UNETR (79.06; 95% CI: 78.33-79.79), MSSegDiff (75.70; 95% CI: 74.97-76.43), and LST-AI (63.19; 95% CI: 62.08-64.30). Normalized DSC followed a similar trend, with SWIMSS reaching 84.88. Lesion detection F1 achieved 81.14. Statistical analyses confirmed its superior performance (p < 0.001). Conclusion: SWIMSS achieved state-of-the-art performance for WM lesion segmentation. By making this model publicly available, we enable broader access to high-quality segmentation tools, allowing smaller centers, often lacking large annotated datasets or computational resources, to benefit from a model trained on a diverse, large-scale cohort. This promotes more equitable access to advanced imaging analysis and supports reproducibility and standardization in MS research.
Source:https://arxiv.org/abs/2611.23351PreviousSurgCBVR: A Multi-Domain Benchmark for Content-Based Surgical Video-to-Video RetrievalNextStreaming Generative Video Compression with Embedding Alignment and In-Context Propagation
Related posts
What Jobs Can a Fresher Get After Learning Python? A Practical Guide
0dev.to
Defensive Coding for Real-Time Scoreboard Components
0dev.to
Dev News Digest: 19 Nov 2026, 06:00
0dev.to News
Download Website as HTML: Get a Runnable Project From a Figma Capture
0dev.to Design
A bilingual article’s canonical URL changes from a draft decision to an API result
0dev.to Discuss
Signs of Wear: Evaluating Intelligent Speed Assistance Under Synthetic Adverse Conditions
0arXiv eess.IV