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

Search research articles

Related Experiment Video

Updated: Apr 8, 2026

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

Deep Learning Approaches for Multiple Sclerosis Detection in MRI Images.

Mohamad Marwan El Sidani¹, Rita Younes¹, Charles Yaacoub²

¹Faculty of Engineering, Université La Sagesse, Beirut, Lebanon.

Biomed Research International

|April 7, 2026

Summary

This summary is machine-generated.

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

AI-driven balance evaluation: a comparative study between blind and non-blind individuals using the mini-BESTest.

PeerJ. Computer science·2025

See all related articles

Deep learning models can automate multiple sclerosis (MS) lesion detection in MRI scans. VGG16 achieved the highest performance, while ResNet-10 offers efficiency for clinical diagnostics.

Area of Science:

Medical Imaging
Artificial Intelligence
Neurology

Background:

Multiple sclerosis (MS) diagnosis relies on MRI, but manual interpretation is slow and variable.
Automating MS lesion detection in MRI is crucial for efficient and accurate diagnostics.

Purpose of the Study:

To evaluate deep learning (DL) models for automated detection of MS lesions in MRI.
To compare the performance of four CNN architectures: AlexNet, VGG16, ResNet-10, and DenseNet-121.

Main Methods:

Utilized four modified CNN architectures (AlexNet, VGG16, ResNet-10, DenseNet-121) on 2831 MRI slices.
Preprocessed data included normalization, resizing, and augmentation.
Trained models using Adam optimizer and binary cross-entropy loss, evaluated with accuracy, precision, recall, and F1-score.

Keywords:

CNN DL MRI MS ResNet VGG16 medical imaging

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Apr 8, 2026

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Main Results:

VGG16 achieved the highest AUC (0.94), precision (0.81), recall (0.93), and F1-score (0.86).
DenseNet-121 (AUC 0.91) and ResNet-10/AlexNet-C (AUC 0.90) also showed strong performance.
ResNet-10 offered the best efficiency-performance balance, suitable for resource-constrained settings.

Conclusions:

DL models show significant potential for automating MS lesion detection in clinical settings.
VGG16 and DenseNet-121 offer high accuracy, while ResNet-10 provides a practical balance for deployment.
Automated detection can lead to more reliable, efficient, and scalable MS diagnostics.