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

Level-crossing processing and deep convolutional neural network for arrhythmia classification in telehealth services.

Physical and engineering sciences in medicine·2025
Same author

ECG based apnea detection by multirate processing hybrid of wavelet-empirical decomposition Hjorth features extraction and neural networks.

PloS one·2023
Same author

Interoperable IoMT Approach for Remote Diagnosis with Privacy-Preservation Perspective in Edge Systems.

Sensors (Basel, Switzerland)·2023
Same author

Security Framework for Network-Based Manufacturing Systems with Personalized Customization: An Industry 4.0 Approach.

Sensors (Basel, Switzerland)·2023
Same author

Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural Network.

Sensors (Basel, Switzerland)·2023
Same author

AI-Powered Diagnosis of Skin Cancer: A Contemporary Review, Open Challenges and Future Research Directions.

Cancers·2023

Related Experiment Video

Updated: Oct 21, 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

48.6K

Multiple Sclerosis Lesion Segmentation in Brain MRI Using Inception Modules Embedded in a Convolutional Neural

Shahab U Ansari1, Kamran Javed1,2, Saeed Mian Qaisar3,4

  • 1Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi, Pakistan.

Journal of Healthcare Engineering
|September 6, 2021
PubMed
Summary

This study introduces an improved convolutional neural network (CNN) for automatic multiple sclerosis (MS) lesion segmentation in brain MRI. The novel framework, incorporating inception modules, achieved superior accuracy compared to human raters.

More Related Videos

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.1K
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

3.1K

Related Experiment Videos

Last Updated: Oct 21, 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

48.6K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.1K
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

3.1K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neurology

Background:

  • Multiple sclerosis (MS) is a chronic autoimmune disease affecting the central nervous system.
  • Accurate segmentation of MS lesions in MRI is crucial for clinical trials and prognosis.
  • Manual lesion segmentation by radiologists is time-consuming and prone to errors.

Purpose of the Study:

  • To develop a novel framework for automatic brain lesion segmentation in MS.
  • To improve the accuracy and efficiency of MS lesion identification in MRI scans.

Main Methods:

  • Proposed a new framework utilizing a novel convolutional neural network (CNN) architecture.
  • Incorporated inception modules, inspired by Google Net, to handle filters of various sizes (1x1, 3x3, 5x5) and max pooling in parallel.
  • Evaluated the CNN architecture using two loss functions: binary cross entropy (BCE) and structural similarity index measure (SSIM).
  • Utilized the publicly available ISBI-2015 challenge dataset for validation.

Main Results:

  • The proposed CNN architecture with inception modules demonstrated improved performance in segmenting MS lesions.
  • Achieved a segmentation score of 93.81% using the BCE loss function.
  • This score surpassed the performance of human raters.

Conclusions:

  • The novel CNN framework with inception modules offers a more accurate and efficient solution for automatic MS lesion segmentation.
  • This approach has the potential to enhance quantitative analysis in MS clinical trials and patient prognosis.