Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Honouring the Past, Shaping the Future.

European neurology·2026

Same author

Challenges and future directions for multiple sclerosis after the 2024 McDonald diagnostic criteria.

Nature medicine·2026

Same author

Postsurgical detection of glioma recurrence using MRI radiomics.

Neuro-oncology advances·2026

Same author

Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data.

ArXiv·2026

Same author

Spinal cord imaging for multiple sclerosis: Advances, priorities, and opportunities.

Multiple sclerosis (Houndmills, Basingstoke, England)·2026

Same author

Fully automatic left ventricle segmentation in [Formula: see text]Rb PET/CT Using a semi-supervised nnU-net.

EJNMMI research·2026

Search research articles

Related Experiment Video

Updated: Jun 3, 2026

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

A comparative study of deep learning for cortical lesion MRI segmentation with explainability analysis in multiple

Nataliia Molchanova¹, Alessandro Cagol², Mario Ocampo-Pineda³

¹Faculty of Biology and Medicine, University of Lausanne (UNIL), Lausanne, Switzerland; Radiology Department, Lausanne University Hospital (CHUV), Lausanne, Switzerland; MedGIFT, Institute of Informatics, School of Management, HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland, Sierre, Switzerland; CIBM Center for Biomedical Imaging, Lausanne, Switzerland.

Neuroimage. Clinical

|June 1, 2026

Summary

This study introduces an AI model for detecting cortical lesions (CLs) in multiple sclerosis (MS) using MRI scans. The model shows promising results, aiding in the clinical application of these important MS biomarkers.

Keywords:

Brain Cortical lesions Deep learning Detection Magnetic resonance imaging Multiple sclerosis Segmentation Trustworthy AI

More Related Videos

Manual Segmentation of the Human Choroid Plexus Using Brain MRI

Manual Segmentation of the Human Choroid Plexus Using Brain MRI

Published on: December 15, 2023

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Related Experiment Videos

Last Updated: Jun 3, 2026

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

Manual Segmentation of the Human Choroid Plexus Using Brain MRI

Manual Segmentation of the Human Choroid Plexus Using Brain MRI

Published on: December 15, 2023

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Area of Science:

Neuroimaging
Artificial Intelligence in Medicine
Biomarker Discovery

Background:

Cortical lesions (CLs) are crucial biomarkers in multiple sclerosis (MS), impacting diagnosis and prognosis.
Current clinical use of CLs is hindered by subtle MRI visibility, expert annotation difficulties, and lack of automated methods.

Purpose of the Study:

To develop and evaluate an automated AI framework for detecting and segmenting cortical lesions in MS using multi-centric MRI data.
To assess the generalizability and performance of the AI model across different imaging protocols and institutions.

Main Methods:

Utilized a large dataset of 656 multi-center MRI scans (3T and 7T) with expert annotations.
Employed and adapted the self-configuring nnU-Net framework for medical image segmentation.
Conducted out-of-distribution testing to evaluate model generalization and analyzed model errors.

Main Results:

Achieved promising F1-scores of 0.64 (in-domain) and 0.5 (out-of-domain) for lesion detection.
Identified key factors influencing model performance, including data variability and imaging protocols.
Gathered clinical value assessment through a medical expert questionnaire.

Conclusions:

The developed AI model demonstrates potential for automated cortical lesion detection in MS, addressing current clinical adoption barriers.
Further research and standardization are recommended to optimize performance and facilitate clinical integration.
Publicly accessible code and models will enhance reproducibility and future development.