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

Percutaneous Extra-Anatomic Splenocaval Shunt Creation for Refractory Portal Hypertensive Bleeding.

Journal of vascular and interventional radiology : JVIR·2026
Same author

Desmoplastic myxoid tumor, SMARCB1-mutant: a case with late recurrence after long-term follow-up.

Free neuropathology·2026
Same author

MAD-MT Score: A Tool to Optimize Patient Selection for Mechanical Thrombectomy in Distal Vessel Occlusions.

Stroke·2026
Same author

Combined stent retriever and contact aspiration improves first-line recanalisation but not clinical outcomes: a pooled analysis of the ASTER, ASTER2, and VECTOR trials.

European stroke journal·2026
Same author

Physician Approaches to Determining Goals of Stroke Care for Patients Living With Disability or Dementia: Results from the SEED Mixed-Methods Study.

Stroke·2026
Same author

Clinical evidence standards for high-risk endovascular devices in ischemic stroke: a European multisociety consensus.

Journal of neurointerventional surgery·2026

Related Experiment Video

Updated: Sep 29, 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

Dense, deep learning-based intracranial aneurysm detection on TOF MRI using two-stage regularized U-Net.

Frédéric Claux1, Maxime Baudouin2, Clément Bogey2

  • 1Univ. Limoges, CNRS, XLIM, UMR 7252, F-87000 Limoges, France.

Journal of Neuroradiology = Journal De Neuroradiologie
|March 21, 2022
PubMed
Summary

A new deep learning tool accurately segments intracranial arteries and detects aneurysms on 3D TOF-MRA scans. This AI aids radiologists in identifying these often-asymptomatic vascular conditions.

Keywords:
Artificial intelligenceCerebral aneurysmDeep learningMagnetic resonance angiography

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.9K
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

Related Experiment Videos

Last Updated: Sep 29, 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
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.9K
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

Area of Science:

  • Neuroradiology
  • Artificial Intelligence in Medical Imaging
  • Neurovascular Imaging

Background:

  • Unruptured intracranial aneurysms are common and often asymptomatic.
  • Diagnosis frequently occurs incidentally via MRI, posing challenges for radiologists.
  • Automated tools are needed to improve efficiency and accuracy.

Purpose of the Study:

  • To develop a deep learning neural network for automated segmentation of intracranial arteries.
  • To create a tool for automated detection of intracranial aneurysms.
  • To utilize 3D time-of-flight magnetic resonance angiography (TOF-MRA) data.

Main Methods:

  • Retrospective extraction of 3D TOF-MRA scans with confirmed aneurysms.
  • Development of a double convolutional neural network (CNN) based on U-Net architecture.
  • Training and testing on small datasets with manual neuroradiologist annotations.

Main Results:

  • The AI tool achieved 78% sensitivity and 62% positive predictive value for aneurysm detection.
  • Average processing time was 15 minutes per case.
  • Detection sensitivity showed no significant difference based on aneurysm size or location.

Conclusions:

  • A deep learning tool effectively segments intracranial arteries and detects aneurysms on 3D TOF-MRA.
  • The U-Net based CNN demonstrates accuracy even with limited training data.
  • This AI offers a promising solution for improving neurovascular diagnostic workflows.