Characterizing spinal cord multiple sclerosis (MS) lesions in MRI is critical for diagnosis, monitoring, and treatment evaluation. However, current automated approaches for lesion detection and segmentation are typically designed for specific MRI contrasts or acquisition sites, limiting their generalizability in real-world clinical settings where imaging protocols vary widely. This work proposes a robust multi-site, multi-contrast segmentation framework for spinal cord lesions.
Methods:
The segmentation model was trained and evaluated on a large-scale dataset comprising 4428 annotated images from 1849 persons with MS across 23 imaging centers, encompassing six MRI contrasts (T1w, T2w, T2*w, PSIR, STIR, and UNIT1) acquired at 1.5 tesla (T), 3 T, and 7 T.
Results:
Likert-type assessment performed by neuroradiologist ratings demonstrated superior generalization of the model compared to existing contrast-specific pipelines (p < 0.01). Additional experiments evaluated robustness across spinal levels, acquisition resolutions, binarization thresholds, and quantitative evaluation on external labeled datasets.
Conclusions:
The proposed model can achieve accurate and reliable spinal cord MS lesion segmentation across heterogeneous MRI data, addressing a key barrier to clinical translation. The model is available in the Spinal Cord Toolbox v7.2 and higher.
WaltonCKingRRechtmanL, et al. Rising prevalence of multiple sclerosis worldwide: Insights from the Atlas of MS, third edition. Mult Scler2020; 26(14): 1816–1821.
2.
WaldmanADCataniaCPisaM, et al. The prevalence and topography of spinal cord demyelination in multiple sclerosis: A retrospective study. Acta Neuropathol2024; 147: 51.
3.
McDonaldWICompstonAEdanG, et al. Recommended diagnostic criteria for multiple sclerosis: Guidelines from the international panel on the diagnosis of multiple sclerosis. Ann Neurol2001; 50(1): 121–127.
4.
ThompsonAJBanwellBLBarkhofF, et al. Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. Lancet Neurol2018; 17: 162–173.
5.
MontalbanXLebrun-FrénayCOhJ, et al. Diagnosis of multiple sclerosis: 2024 revisions of the McDonald criteria. Lancet Neurol2025; 24: 850–865.
6.
KerbratAGrosCBadjiA, et al. Multiple sclerosis lesions in motor tracts from brain to cervical cord: Spatial distribution and correlation with disability. Brain2020; 143: 2089–2105.
7.
Jackson-TarltonCSFlanaganEPMessinaSA, et al. Progressive motor impairment from “critical” demyelinating lesions of the cervicomedullary junction. Mult Scler2023; 29(1): 74–80.
8.
AhmadRJackson-TarltonCSFlanaganEP, et al. Critical demyelinating lesions in progressive multiple sclerosis: A prospective observational study. J Neurol2025; 272: 677.
9.
DemortièreSLehmannPPelletierJ, et al. Improved cervical cord lesion detection with 3D-MP2RAGE sequence in patients with Multiple Sclerosis. AJNR Am J Neuroradiol2020; 41(6): 1131–1134.
10.
StromanPWWheeler-KingshottCBaconM, et al. The current state-of-the-art of spinal cord imaging: Methods. Neuroimage2014; 84: 1070–1081.
11.
SaslowLLiDKBHalperJ, et al. An international standardized magnetic resonance imaging protocol for diagnosis and follow-up of patients with multiple sclerosis: Advocacy, dissemination, and implementation strategies. Int J MS Care2020; 22(5): 226–232.
12.
Cohen-AdadJAlonso-OrtizEAbramovicM, et al. Generic acquisition protocol for quantitative MRI of the spinal cord. Nat Protoc2021; 16(10): 4611–4632.
13.
BarkhofFReichDSOhJ, et al. 2024 MAGNIMS-CMSC-NAIMS consensus recommendations on the use of MRI for the diagnosis of multiple sclerosis. Lancet Neurol2025; 24(10): 866–879.
14.
WattjesMPCiccarelliOReichDS, et al. 2021 MAGNIMS-CMSC-NAIMS consensus recommendations on the use of MRI in patients with multiple sclerosis. Lancet Neurol2021; 20(8): 653–670.
15.
GuttmannCRKikinisRAndersonMC, et al. Quantitative follow-up of patients with multiple sclerosis using MRI: Reproducibility. J Magn Reson Imaging1999; 9(4): 509–518.
16.
KaurAKaurLSinghA.State-of-the-art segmentation techniques and future directions for multiple sclerosis brain lesions. Arch Computat Methods Eng2021; 28: 951–977.
17.
AslaniSDayanMStorelliL, et al. Multi-branch convolutional neural network for multiple sclerosis lesion segmentation. Neuroimage2019; 196: 1–15.
18.
ValverdeSCabezasMRouraE, et al. Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach. Neuroimage2017; 155: 159–168.
19.
HavaeiMGuizardNChapadosN, et al. HeMIS: Hetero-modal image segmentation. In: OurselinSJoskowiczLSabuncuMR, et al. (eds) Medical image computing and computer-assisted intervention—MICCAI 2016. Cham: Springer International Publishing, 2016, pp. 469–477.
20.
EssaEAldesoukyDHusseinSE, et al. Neuro-fuzzy patch-wise R-CNN for multiple sclerosis segmentation. Med Biol Eng Comput2020; 58(9): 2161–2175.
21.
GessertNBengsMKrügerJ, et al. 4D deep learning for multiple sclerosis lesion activity segmentation 2020, http://arxiv.org/abs/2004.09216
22.
KamraouiRATaVTTourdiasT, et al. DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation. Med Image Anal2022; 76: 102312.
23.
WiltgenTMcGinnisJSchlaegerS, et al. LST-AI: A deep learning ensemble for accurate MS lesion segmentation. medRxiv. Epub ahead of print 11 March 2024. DOI: 10.1101/2023.11.23.23298966.
24.
ZengCGuLLiuZ, et al. Review of deep learning approaches for the segmentation of multiple sclerosis lesions on brain MRI. Front Neuroinform2020; 14: 610967.
25.
LodéBHusseinBRMeuréeC, et al. Evaluation of a deep learning segmentation tool to help detect spinal cord lesions from combined T2 and STIR acquisitions in people with multiple sclerosis. Eur Radiol2025; 35(10): 5954–5964.
26.
WalshRMeuréeCKerbratA, et al. Expert variability and deep learning performance in spinal cord lesion segmentation for multiple sclerosis patients. In: 2023 IEEE 36th international symposium on computer-based medical systems (CBMS), L’Aquila, 22–24 June 2023, pp. 463–470. New York: IEEE.
27.
PolattímurRDandilEYildirimMS, et al. FractalSpiNet: Fractal-based U-net for automatic segmentation of cervical spinal cord and MS lesions in MRI. IEEE Access2024; 12: 110955–110976.
28.
GrosCDe LeenerBBadjiA, et al. Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. Neuroimage2019; 184: 901–915.
29.
BenvenisteP-LValošekJChenM, et al. Automatic segmentation of spinal cord multiple sclerosis lesions across multiple sites, contrasts and vendors. In: 32th annual meeting of ISMRM, Singapore, 4–9 May 2024.
30.
MedinaNLMchindaSTestudB, et al. Automatic multiple sclerosis lesion segmentation in the spinal cord on 3T and 7T MP2RAGE images. In: 33th annual meeting of ISMRM, Honolulu, HI, 10–15 May 2025.
31.
Naga KarthikEMcGinnisJWurmR, et al. Automatic segmentation of spinal cord lesions in MS: A robust tool for axial T2-weighted MRI scans. Imaging Neurosci2025; 3: IMAG.a.45.
32.
KarimiDDouHWarfieldSK, et al. Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis. Med Image Anal2020; 65: 101759.
33.
OktayOSchlemperJFolgocLL, et al. Attention U-Net: Learning where to look for the pancreas. arXiv. Epub ahead of print 20 May 2018. DOI: 10.48550/arXiv.1804.03999.
34.
HuangZWangHDengZ, et al. STU-Net: Scalable and transferable medical image segmentation models empowered by large-scale supervised pre-training. arXiv. Epub ahead of print 13 April 2023. DOI: 10.48550/arXiv.2304.06716.
35.
UlrichCWaldTIsenseeF, et al. Large scale supervised pretraining for traumatic brain injury segmentation. arXiv. Epub ahead of print 9 April 2025. DOI: 10.48550/arXiv.2504.06741.
36.
RoySKoehlerGUlrichC, et al. MedNeXt: Transformer-driven scaling of ConvNets for medical image segmentation. In: GreenspanH (ed.) Lecture notes in computer science. Cham: Springer Nature, 2023, pp. 405–415.
37.
IsenseeFJaegerPFKohlSAA, et al. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat Methods2021; 18(2): 203–211.
38.
KeskarNSMudigereDNocedalJ, et al. On large-batch training for deep learning: Generalization gap and sharp minima. arXiv. Epub ahead of print 9 February 2016. DOI: 10.48550/arXiv.1609.04836.
39.
GrosCLemayACohen-AdadJ.SoftSeg: Advantages of soft versus binary training for image segmentation. Med Image Anal2021; 71: 102038.
40.
ArpitDJastrzebskiSBallasN, et al. A closer look at memorization in deep networks. ICML2017; 70: 233–242.
41.
IsenseeFWaldTUlrichC, et al. NnU-net revisited: A call for rigorous validation in 3D medical image segmentation. In: LinguraruMG (ed.) Lecture notes in computer science. Cham: Springer Nature, 2024, pp. 488–498.
42.
PetersSNevesFBHuhndorfM, et al. Detection of spinal cord multiple sclerosis lesions using a 3D-PSIR sequence at 1.5 T. Clin Neuroradiol2024; 34(2): 403–410.
43.
GallerSStellmannJPYoungKL, et al. Improved lesion detection by using axial T2-weighted MRI with full spinal cord coverage in multiple sclerosis. AJNR Am J Neuroradiol2016; 37(5): 963–969.
44.
WarszawerYMolinierNValošekJ, et al. TotalSpineSeg: Robust segmentation and labeling of vertebrae, intervertebral discs, spinal cord, and spinal canal in MRI images using nnU-Net and iterative algorithm. Geneva: Zenodo, 2024.
45.
UlrichCIsenseeFWaldT, et al. MultiTalent: A multi-dataset approach to medical image segmentation. In: GreenspanH (ed.) Lecture notes in computer science. Cham: Springer Nature, 2023, pp. 648–658.
46.
Maier-HeinLReinkeAGodauP, et al. Metrics reloaded: Recommendations for image analysis validation. Nat Methods2024; 21(2): 195–212.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
