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

Generalizable and explainable deep learning for brain MRI: a multi-cohort evaluation of 3D architectures for age and sex prediction.

Brain informatics·2026
Same author

Multi-modal data integration reveals functionally credible predictive biomarkers in ovarian cancer.

Genome medicine·2026
Same author

On the utility of ChatGPT in conducting a literature review on deep learning for dopamine transporter SPECT with [¹²³I]ioflupane.

Nuklearmedizin. Nuclear medicine·2026
Same author

Expert Panel Consensus Guidelines of the German Society of Neuroradiology on the Use of Magnetic Resonance Imaging in the Diagnosis and Monitoring of Multiple Sclerosis.

Clinical neuroradiology·2026
Same author

A review of deep learning-based Unsupervised Anomaly Detection in brain MRI.

Medical image analysis·2026
Same author

Cognition and fatigue in clinically stable multiple sclerosis: EDSS and MRI metrics outperform serum biomarkers.

BMC neurology·2026

Related Experiment Video

Updated: Dec 12, 2025

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

49.1K

Multiple sclerosis lesion activity segmentation with attention-guided two-path CNNs.

Nils Gessert1, Julia Krüger2, Roland Opfer2

  • 1Hamburg University of Technology, Institute of Medical Technology, Am Schwarzenberg-Campus 3, 21073 Hamburg, Germany.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|August 16, 2020
PubMed
Summary
This summary is machine-generated.

Deep learning models, specifically convolutional neural networks (CNNs), show promise for segmenting new and enlarging lesions in multiple sclerosis (MS) by analyzing MRI scans from two time points. Attention-guided CNNs significantly improve lesion activity detection compared to traditional methods.

Keywords:
AttentionDeep learningLesion activityMultiple sclerosisSegmentation

More Related Videos

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

40.7K
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

3.5K

Related Experiment Videos

Last Updated: Dec 12, 2025

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

49.1K
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

40.7K
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

3.5K

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Medical Image Analysis

Background:

  • Multiple sclerosis (MS) is an inflammatory autoimmune disease affecting the central nervous system, typically monitored using magnetic resonance imaging (MRI).
  • Current MRI analysis often focuses on segmenting lesions in individual scans, but tracking lesion activity (new or enlarging lesions) between time points is critical for disease progression monitoring.
  • Deep learning methods are underutilized for lesion activity segmentation, despite their success in single-scan lesion segmentation.

Purpose of the Study:

  • To investigate the efficacy of convolutional neural networks (CNNs) for segmenting lesion activity in multiple sclerosis (MS) using paired MRI scans from two time points.
  • To develop and evaluate novel CNN architectures, particularly two-path approaches with attention-guided interactions, for improved lesion activity detection.

Main Methods:

  • Development and evaluation of CNNs designed to process and integrate information from MRI scans at two distinct time points.
  • Implementation of two-path architectures with attention-guided mechanisms to facilitate effective information exchange between temporal data streams.
  • Comparison of deep learning-based methods against classic difference-volume approaches for lesion activity segmentation.

Main Results:

  • Deep learning methods, especially those employing attention-guided interactions, significantly outperformed classic approaches in lesion activity segmentation.
  • Attention modules generated interpretable attention maps that effectively suppressed irrelevant (older) lesions.
  • Achieved a lesion-wise false positive rate of 26.4% at a true positive rate of 74.2%, comparable to interrater reliability.

Conclusions:

  • CNNs with attention-guided interactions represent a powerful tool for automated lesion activity segmentation in multiple sclerosis.
  • These deep learning approaches offer a significant advancement over traditional methods for monitoring disease progression via MRI.
  • The developed method demonstrates high performance and potential for clinical application in MS management.