Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Closing the Carbon Loop: Continuous-Flow Synthesis of N-Aroyl Sulfoximines via Electrochemical CO<sub>2</sub> Reduction.

ChemSusChem·2026
Same author

Safety Profile of Zavegepant in the Treatment of Acute Migraine: Insights from the FDA Adverse Event Monitoring System Database.

Pharmaceuticals (Basel, Switzerland)·2026
Same author

Assessing Cat Welfare: A Literature Review on Behavioural, Physiological and Health Parameters with a Focus on Animal-Assisted Services (AAS).

Veterinary sciences·2026
Same author

Use of High-Efficacy Therapy in Children With Multiple Sclerosis to Prevent Long-Term Disability.

Neurology·2026
Same author

Anti-Inflammatory Activity of In Vitro Digested Manna in a Caco-2 and RAW264.7 Cells Co-Culture Model of Inflammatory Bowel Disease.

Antioxidants (Basel, Switzerland)·2026
Same author

Comparative effectiveness of ocrelizumab in subgroups of patients with multiple sclerosis: a multi-registry observational cohort study.

Journal of neurology, neurosurgery, and psychiatry·2026

Related Experiment Video

Updated: Jul 29, 2025

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

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

40.3K

Boosting multiple sclerosis lesion segmentation through attention mechanism.

Alessia Rondinella1, Elena Crispino2, Francesco Guarnera1

  • 1Department of Mathematics and Computer Science, University of Catania, Viale Andrea Doria 6, Catania, 95125, Italy.

Computers in Biology and Medicine
|May 22, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces an AI framework for automated multiple sclerosis lesion segmentation in MRI scans. The novel approach significantly improves accuracy and robustness compared to existing methods.

Keywords:
AttentionFully convolutional neural networkIn Silico Trials (IST)Lesion segmentationMagnetic resonance imaging (MRI)Medical image analysisMultiple sclerosis (MS)

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

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

Published on: September 25, 2019

48.1K

Related Experiment Videos

Last Updated: Jul 29, 2025

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

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

40.3K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

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

Published on: September 25, 2019

48.1K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neurology

Background:

  • Magnetic resonance imaging (MRI) is crucial for multiple sclerosis (MS) diagnosis and progression monitoring.
  • Current AI-based lesion segmentation methods lack full automation and rely on incremental architectural improvements.
  • Temporal features and attention mechanisms show promise for enhancing segmentation performance.

Purpose of the Study:

  • To develop a fully automated framework for segmenting and quantifying multiple sclerosis lesions in MRI.
  • To improve upon state-of-the-art AI methods for MS lesion analysis.

Main Methods:

  • An augmented U-Net architecture was developed, incorporating a convolutional long short-term memory layer and an attention mechanism.
  • The framework was designed to exploit temporal-aware features for enhanced segmentation.
  • The method was evaluated using quantitative and qualitative analyses on challenging datasets.

Main Results:

  • The proposed framework achieved an overall Dice score of 89%, outperforming previous state-of-the-art approaches.
  • Demonstrated robustness and generalization ability on unseen test samples.
  • Successfully segmented and quantified multiple sclerosis lesions in MRI scans.

Conclusions:

  • The developed AI framework offers a significant advancement in automated multiple sclerosis lesion segmentation.
  • The integration of temporal features and attention mechanisms enhances segmentation accuracy and reliability.
  • This method holds potential for improved clinical diagnosis and monitoring of multiple sclerosis.