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

Seizures: Classification01:13

Seizures: Classification

378
Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
378

You might also read

Related Articles

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

Sort by
Same author

Adaptation of rhizobacterial and endophytic communities in <i>Citrus Grandis Exocarpium</i> to long-term organic and chemical fertilization.

Frontiers in microbiology·2024
Same author

PD-1/PD-L1 and coronary heart disease: a mendelian randomization study.

Frontiers in cardiovascular medicine·2024
Same author

Differentiation of MOGAD in ADEM-like presentation children based on FLAIR MRI features.

Multiple sclerosis and related disorders·2023
Same author

Evaluation of the Antidepressant Effect of the Functional Beverage Containing Active Peptides, Menthol and Eleutheroside and Investigation of Its Mechanism of Action in Mice.

Food technology and biotechnology·2020
Same author

CO oxidation over AuPd(100) from ultrahigh vacuum to near-atmospheric pressures: the critical role of contiguous Pd atoms.

Journal of the American Chemical Society·2009
Same author

Daunorubicin-loaded magnetic nanoparticles of Fe(3)O(4) greatly enhance the responses of multidrug-resistant K562 leukemic cells in a nude mouse xenograft model to chemotherapy.

Zhongguo shi yan xue ye xue za zhi·2009

Related Experiment Video

Updated: Jul 12, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

M-DDC: MRI based demyelinative diseases classification with U-Net segmentation and convolutional network.

Deyang Zhou1, Lu Xu2, Tianlei Wang3

  • 1Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, 310018, China; Artificial Intelligence Institute, Hangzhou Dianzi University, Zhejiang, 310018, China; HDU-ITMO Joint Institute, Hangzhou Dianzi University, Zhejiang, 310018, China.

Neural Networks : the Official Journal of the International Neural Network Society
|October 27, 2023
PubMed
Summary
This summary is machine-generated.

A new M-DDC deep learning model accurately classifies childhood demyelinating diseases using brain MRI. This method distinguishes between acute disseminated encephalomyelitis (ADEM) and neuromyelitis optica spectrum disorder (NMOSD) with high precision.

Keywords:
Deep learningImage classificationImage segmentationMagnetic resonance imagingPediatric demyelinating diseaseU-Net

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.9K

Related Experiment Videos

Last Updated: Jul 12, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.9K

Area of Science:

  • Neurology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Childhood demyelinating diseases (DDC) require accurate classification for effective treatment.
  • Differentiating pediatric-onset neuromyelitis optica spectrum disorder (NMOSD) from acute disseminated encephalomyelitis (ADEM) using brain MRI is a significant diagnostic challenge.
  • Existing classification methods for DDC lack sufficient accuracy.

Purpose of the Study:

  • To develop a novel deep learning architecture, M-DDC, for accurate classification of childhood demyelinating diseases.
  • To improve the differentiation between ADEM and NMOSD using brain MRI.
  • To leverage U-Net segmentation and deep convolutional networks for enhanced diagnostic capabilities.

Main Methods:

  • A novel M-DDC architecture was developed, integrating a U-Net segmentation network with a deep convolutional network.
  • The U-Net component provides pixel-level structural information for lesion localization and size estimation.
  • The classification branch identifies regions of interest, including white matter lesions, within MRIs.

Main Results:

  • The M-DDC model achieved a high accuracy of 99.19% for classifying ADEM and NMOSD.
  • The model demonstrated a dice score of 71.1% for lesion segmentation in pediatric DDC.
  • Performance was validated on a dataset of 201 subjects from Children's Hospital of Zhejiang University School of Medicine.

Conclusions:

  • The proposed M-DDC architecture offers a highly accurate and effective solution for classifying childhood demyelinating diseases.
  • This method significantly enhances the ability to differentiate between ADEM and NMOSD based on brain MRI.
  • The joint segmentation and classification approach holds promise for improving DDC diagnosis in pediatric neurology.