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

LOTUS: Latent Outpainting Diffusion Model for Three-Dimensional Ultrasound Stitching.

Proceedings of machine learning research·2026
Same author

Pituitary Axis Impacts and Effectiveness of Clomiphene and Human Chorionic Gonadotropin in Treating Hypogonadism: Cohort Study.

The world journal of men's health·2026
Same author

Molecular maps of diseases from omics data and network embeddings.

NPJ systems biology and applications·2026
Same author

Scaling Multimodal Agentic AI in Medical Education: Multisite Cross-Sectional Study of Simulation Effectiveness in Primary Care.

JMIR formative research·2026
Same author

Beyond Weight Loss: Holistic Impacts of a Digital Weight Management Programme Integrating Tirzepatide.

Cureus·2026
Same author

Digital Engagement Significantly Enhances Weight Loss Outcomes in Adults With Obesity Treated With Tirzepatide: Retrospective Cohort Study of a Digital Weight Loss Service.

Journal of medical Internet research·2026

Related Experiment Video

Updated: Sep 8, 2025

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

9.0K

Generalizing MRI Subcortical Segmentation to Neurodegeneration.

Hao Li1, Huahong Zhang1, Dewei Hu1

  • 1Department of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, USA.

Machine Learning in Clinical Neuroimaging and Radiogenomics in Neuro-Oncology : Third International Workshop, MLCN 2020, and Second International Workshop, RNO-AI 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4-8, 2020
|June 13, 2022
PubMed
Summary

This study enhances LiviaNET, a deep learning model for brain MRI segmentation, improving its accuracy in neurodegenerative diseases like Huntington's disease. The modified model shows better generalization for patient data without retraining.

Keywords:
MRINeurodegenerationSegmentationSubcortical

More Related Videos

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
09:06

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

12.2K
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

48.4K

Related Experiment Videos

Last Updated: Sep 8, 2025

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

9.0K
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
09:06

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

12.2K
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

48.4K

Area of Science:

  • Neuroimaging
  • Deep Learning
  • Neurodegenerative Diseases

Background:

  • Neurodegenerative diseases like Huntington's disease impact subcortical brain structures.
  • Accurate segmentation of subcortical structures (caudate, putamen) from MRI is crucial for HD research.
  • Current deep learning models like LiviaNET require extensive disease-specific training data, which is costly to acquire.

Purpose of the Study:

  • To enhance the LiviaNET deep learning model for improved generalization to neurodegenerative disease populations.
  • To investigate strategies for improving LiviaNET's performance on MRI scans of patients with significant neurodegeneration.
  • To reduce the need for costly, disease-specific data annotation for subcortical segmentation.

Main Methods:

  • Implemented Res-blocks within the convolutional neural network architecture.
  • Explored input manipulation techniques for the network.
  • Utilized random elastic deformations for data augmentation.
  • Trained and tested model variants on the PREDICT-HD dataset, including control and Huntington's disease subjects.

Main Results:

  • Achieved improved segmentation accuracy for most subcortical structures in both control and HD subjects compared to the original LiviaNET.
  • Demonstrated the most significant improvement in the segmentation of the caudate nucleus in HD subjects.
  • The modifications enhanced the model's ability to segment structures affected by substantial neurodegeneration.

Conclusions:

  • The proposed modifications to LiviaNET improve its generalization ability for segmenting subcortical structures in neurodegenerative disease cohorts.
  • These enhancements allow for more accurate analysis of brain structures affected by diseases like Huntington's disease without requiring retraining on patient data.
  • The study highlights the potential of LiviaNET variants for broader application in clinical neuroimaging research.