Deep Learning-Based Multiple Sclerosis Lesion Segmentation at 7 Tesla: Comparison of Single- and Multi-Contrast MRI Inputs
Authors:
- Anna PetrovaAPAnna Petrova
- Ivan PetrovicIPIvan Petrovic
- Marc BergerMBMarc Berger
- Yanniklas KravutskeYKYanniklas Kravutske
- Joel LeinkaufJLJoel Leinkauf
- Rebeka RumbakRRRebeka Rumbak
- Lukas HaiderLHLukas Haider
- Eva NiessENEva Niess
- Bernhard StrasserBSBernhard Strasser
- Wolfgang BognerWolfgang Bogner
- Günther GrabnerGGGünther Grabner
- Gabriel BstehGBGabriel Bsteh
Open Access
- 14 October 2026
- journal article
- research article
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (10) , 510
Abstract
Automated lesion segmentation can support rapid and reproducible quantitative assessment and long-term monitoring of multiple sclerosis. Ultra-high-field 7T MRI provides increased spatial resolution and lesion visibility but introduces challenges for automated analysis, including field inhomogeneity, susceptibility-related artifacts, and spatially varying image contrast. Although deep learning methods perform well at conventional field strengths, their application to 7T MRI remains underexplored. We evaluated nnUNet using FLAIR alone, MP2RAGE alone, and combined MP2RAGE+FLAIR. The dataset included 115 longitudinal 7T MRI scans from 57 patients with MS, with 20 scans from 11 independent patients reserved for testing. DeepMedic was included as a comparative architecture. On the test set, nnUNet achieved mean DSC values of 0.72, 0.71, and 0.66 for combined, MP2RAGE-only, and FLAIR-only inputs, respectively. No significant DSC differences were observed between nnUNet and DeepMedic. For both architectures, adding FLAIR to MP2RAGE did not show a statistically significant additional benefit in the present test cohort, whereas MP2RAGE-containing inputs significantly outperformed FLAIR-only input. The findings of the present study provide preliminary evidence suggesting that the observed voxel-level segmentation performance was primarily associated with the inclusion of MP2RAGE. However, lesion-level performance depended on lesion size, indicating further investigation of contrast-specific effects on small-lesion detection.Keywords
Funding Information
- F. Hoffmann-La Roche, Basel (FA761A1147)
This publication has 28 references indexed in Scilit:
- Dual-domain attention Mamba-based 3D U-net architecture for multiple sclerosis lesion segmentationJournal of Radiation Research and Applied Sciences, 2025
- Multiple sclerosis cortical lesion detection with deep learning at ultra‐high‐field MRINMR in Biomedicine, 2022
- DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentationMedical Image Analysis, 2022
- Automated volumetric assessment with artificial neural networks might enable a more accurate assessment of disease burden in patients with multiple sclerosisEuropean Radiology, 2020
- Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentationMedical Image Analysis, 2017
- FSLNeuroImage, 2012
- An automated tool for detection of FLAIR-hyperintense white-matter lesions in Multiple SclerosisNeuroImage, 2012
- Lesion detection at seven Tesla in multiple sclerosis using magnetisation prepared 3D-FLAIR and 3D-DIREuropean Radiology, 2011
- MP2RAGE, a self bias-field corrected sequence for improved segmentation and T1-mapping at high fieldNeuroImage, 2010
- User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliabilityNeuroImage, 2006