Automated segmentation of multiple sclerosis lesions, paramagnetic rims, and central vein sign on MRI provides reliable diagnostic biomarkers

Multiple sclerosis (MS) is characterized by central nervous system lesions detectable via MRI. Existing diagnostic criteria incorporate presence of white matter lesions, but specificity can be improved using MS-specific imaging biomarkers, including paramagnetic rim lesions (PRLs) and central vein sign (CVS). However, manual segmentation of lesions, PRLs, and CVS is time-consuming and subjective. We propose a fully-automated joint segmentation method called Automated Lesion, PRL, and CVS Analysis (ALPaCA). We trained ALPaCA using subject-level cross-validation on 47 adults with MS and 50 adults with radiological MS mimics. ALPaCA uses a voxel-wise lesion segmentation method to propose a large set of lesion candidates. Lesion candidates are input into a multi-contrast, multi-label 3D convolutional neural network as 3D patches to produce lesion, PRL, and CVS predictions. When multiple lesions exist within a patch, an attention mechanism identifies which lesion candidate to classify. At the lesion level, ALPaCA achieves cross-validation areas under the receiver operating characteristic curve (AUROCs) of 0.95, 0.91, and 0.87 for lesion, PRL, and CVS classification, outperforming previous methods (all p < 0.001). Correlations between subject-level ALPaCA lesion and PRL scores with manual counts are higher than those of previous methods (p < 0.001; p = 0.03). Subject-level ALPaCA PRL and CVS scores are highly associated with MS in logistic regressions, when controlling for age and sex (p < 0.001). ALPaCA allows for fully-automated simultaneous segmentation of MS lesions, PRLs, and CVS using clinically-feasible scans. These segmentations outperform existing methods at the lesion and subject level.

Authors

Institutions

Publication Details

Journal
Imaging Neuroscience
Published
2025-01-01
DOI
https://doi.org/10.1162/imag.a.932
Citations
1
Primary Topic
Multiple Sclerosis Research Studies
Type
article
Field-Weighted Citation Impact
1.47

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Automated segmentation of multiple sclerosis lesions, paramagnetic rims, and central vein sign on MRI provides reliable diagnostic biomarkers

Carolyn Lou, Martina Absinta, Jiwon Oh, Léorah Freeman et al.
1 citations
Imaging Neuroscience
Multiple Sclerosis Research Studies
1.47
article

Automated segmentation of multiple sclerosis lesions, paramagnetic rims, and central vein sign on MRI provides reliable diagnostic biomarkers

Carolyn Lou, Martina Absinta, Jiwon Oh, Léorah Freeman, Andrew J Solomon, Michel Bilello, Daniel Ontaneda, Kelly Clark, Zheng Ren, Daniel S. Reich, Brian Renner, Erin E. Longbrake, Jordan D. Dworkin, Fengling Hu, Russell Taki Shinohara, Lynn Daboul, Theodore Daniel Satterthwaite, Matthew K. Schindler, Carly M. O’Donnell, Abigail R. Manning, Luyun Chen, Haochang Shou, Peter A. Calabresi, Roland G. Henry, Elizabeth D. Verter, Alessandra M. Valcarcel, Nancy L. Sicotte, C.W. Chen, Eunchan Bae, Amit Bar‐Or, Kunio Nakamura, Pascal Sati
article en
1 citations

Abstract

Multiple sclerosis (MS) is characterized by central nervous system lesions detectable via MRI. Existing diagnostic criteria incorporate presence of white matter lesions, but specificity can be improved using MS-specific imaging biomarkers, including paramagnetic rim lesions (PRLs) and central vein sign (CVS). However, manual segmentation of lesions, PRLs, and CVS is time-consuming and subjective. We propose a fully-automated joint segmentation method called Automated Lesion, PRL, and CVS Analysis (ALPaCA). We trained ALPaCA using subject-level cross-validation on 47 adults with MS and 50 adults with radiological MS mimics. ALPaCA uses a voxel-wise lesion segmentation method to propose a large set of lesion candidates. Lesion candidates are input into a multi-contrast, multi-label 3D convolutional neural network as 3D patches to produce lesion, PRL, and CVS predictions. When multiple lesions exist within a patch, an attention mechanism identifies which lesion candidate to classify. At the lesion level, ALPaCA achieves cross-validation areas under the receiver operating characteristic curve (AUROCs) of 0.95, 0.91, and 0.87 for lesion, PRL, and CVS classification, outperforming previous methods (all p < 0.001). Correlations between subject-level ALPaCA lesion and PRL scores with manual counts are higher than those of previous methods (p < 0.001; p = 0.03). Subject-level ALPaCA PRL and CVS scores are highly associated with MS in logistic regressions, when controlling for age and sex (p < 0.001). ALPaCA allows for fully-automated simultaneous segmentation of MS lesions, PRLs, and CVS using clinically-feasible scans. These segmentations outperform existing methods at the lesion and subject level.

Imaging NeuroscienceVol. 3
University of Vermont (US), Roche (Switzerland) (CH), Cedars-Sinai Medical Center (US), Brigham and Women's Hospital (US), St. Michael's Hospital (CA), Cleveland Clinic (US), Humanitas University (IT), Johns Hopkins University (US), University of California, San Francisco (US), Pfizer (United States) (US), University of Toronto (CA), Johns Hopkins Medicine (US), Yale University (US), Cleveland Clinic Lerner College of Medicine (US), Dell Children's Medical Center of Central Texas (US), National Institute of Neurological Disorders and Stroke (US), Laboratoire d’Imagerie Biomédicale (FR), Penn Center for AIDS Research (US), DELL (United States) (US), Lifespan (US), IRCCS Humanitas Research Hospital (IT), University of Pennsylvania (US), The University of Texas at Austin (US)
Conrad N. Hilton Foundation, Amgen, Bristol-Myers Squibb, Sanofi, Biogen, Patient-Centered Outcomes Research Institute, Alexion Pharmaceuticals, TG Therapeutics, International Progressive MS Alliance, Horizon Therapeutics, Multiple Sclerosis Society, Fondazione Cariplo, National Institutes of Health, Genentech, EMD Serono, Sanofi Genzyme, National Institute of Neurological Disorders and Stroke
Openalex Percentile: Top 15%
Multiple Sclerosis Research Studies
1.47
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.