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

Expanding the phenotypic spectrum of RYBP-related neurodevelopmental disorder: report of the ninth patient worldwide.

Neurologia i neurochirurgia polska·2026
Same author

Machine-learning-based cardiovascular mortality prediction using a cumulative PM<sub>2.5</sub> exposure metric in high risk groups: a retrospective cohort study.

Scientific reports·2026
Same author

Detecting cardiovascular diseases using ECG scans and explainable artificial intelligence.

Computer methods and programs in biomedicine·2026
Same author

Hemispheric surgery for hemimegalencephaly and hemispheric cortical dysplasia in infants below 12 months of age-A single-center experience.

Epilepsia·2026
Same author

Revised recommendations of the Polish Medical Society of Radiology and the Polish Neurological Society for a protocol concerning routinely used magnetic resonance imaging in patients with multiple sclerosis.

Neurologia i neurochirurgia polska·2026
Same author

Cognitive and clinical associations with lesion load and EEG microstate alterations in multiple sclerosis.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026

Related Experiment Video

Updated: Oct 5, 2025

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

3.0K

Segmenting pediatric optic pathway gliomas from MRI using deep learning.

Jakub Nalepa1, Szymon Adamski2, Krzysztof Kotowski2

  • 1Department of Algorithmics and Software, Silesian University of Technology, Gliwice, Poland; Graylight Imaging, Gliwice, Poland.

Computers in Biology and Medicine
|January 25, 2022
PubMed
Summary

A new deep learning algorithm automatically detects and segments optic pathway gliomas from MRI scans. This reproducible method accurately assesses tumor burden, aiding clinical management and potentially detecting other brain tumors.

Keywords:
Deep learningHGGLGGOptic pathway gliomaPre-trainingSegmentationTransfer learning

More Related Videos

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

3.0K
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

Related Experiment Videos

Last Updated: Oct 5, 2025

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

3.0K
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

3.0K
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

Area of Science:

  • Neuro-oncology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Optic pathway gliomas are pediatric brain tumors requiring accurate tumor burden assessment via MRI.
  • Manual segmentation of these tumors is challenging, time-consuming, and prone to errors.
  • Developing automated methods is crucial for efficient clinical management.

Purpose of the Study:

  • To develop a fully-automatic deep learning algorithm for detecting and segmenting optic pathway gliomas from MRI.
  • To create a reproducible and well-generalizing model, even with limited training data.
  • To evaluate the algorithm's accuracy in volumetric measurements and its potential for detecting other brain tumors.

Main Methods:

  • A deep learning algorithm was developed using recent advancements in the field.
  • Training strategies were optimized for generalization with limited ground-truth data.
  • The algorithm was rigorously tested on two clinical datasets and one public glioma dataset.

Main Results:

  • The algorithm accurately detected and segmented optic pathway gliomas.
  • High agreement was observed between automated and ground-truth volumetric measurements.
  • The approach demonstrated fast operation and potential for detecting other brain tumors.
  • The deep learning architectures were made open-source for reproducibility.

Conclusions:

  • The proposed deep learning algorithm offers an effective, automatic, and reproducible solution for optic pathway glioma segmentation from MRI.
  • The technique shows promise for improving clinical utility in tumor burden assessment and broader brain tumor detection.
  • Open-sourcing the architecture ensures transparency and facilitates further research and application.