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

Type II Endoleak After EVAR: The Sac Behavior-Anatomy Driven Management (SADM) Framework.

Annals of vascular surgery·2026
Same author

Pulmonary Aspergillosis in an Infant with Multiple Hepatic Hemangiomas.

Children (Basel, Switzerland)·2026
Same author

Assessment of the usefulness of ultrasound in the diagnosis of skull fractures in children - a five-year institutional experience.

Journal of ultrasonography·2026
Same author

Brachial Arteriovenous Fistula After Coronary Angiography via Radial Access: First Reported Case of Unexpected Complication.

The Canadian journal of cardiology·2025
Same author

Viral Infection Correlates with a Better Clinical Outcome than Pulmonary Exacerbation of Bacterial Origin in Paediatric Patients with Cystic Fibrosis.

Pathogens (Basel, Switzerland)·2025
Same author

When appendicitis mimics a liver abscess: diagnostic challenges in pediatric surgery.

Journal of surgical case reports·2025

Related Experiment Video

Updated: Dec 13, 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

3.2K

Deep learning for cerebral angiography segmentation from non-contrast computed tomography.

Michał Klimont1,2, Agnieszka Oronowicz-Jaśkowiak2,3, Mateusz Flieger2

  • 1Department of Radiology, Poznań University of Medical Sciences, Poznań, Poland.

Plos One
|August 1, 2020
PubMed
Summary

Deep learning models can segment cerebral arteries from non-contrast computed tomography scans, enabling contrast-free angiography. This overcomes limitations of traditional imaging for vascular pathology diagnosis.

More Related Videos

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.3K
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

3.5K

Related Experiment Videos

Last Updated: Dec 13, 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

3.2K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.3K
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

3.5K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Cerebral computed tomography angiography (CTA) is crucial for diagnosing vascular pathologies but requires contrast media.
  • Contrast administration has contraindications, necessitating alternative imaging like magnetic resonance angiography.
  • Non-contrast computed tomography (CT) alone is insufficient for evaluating cerebral arteries due to poor distinguishability from brain tissue.

Purpose of the Study:

  • To apply deep learning for segmenting cerebral arteries on non-contrast CT scans.
  • To generate contrast-free angiographies using segmented artery data.
  • To overcome limitations associated with contrast media in cerebral angiography.

Main Methods:

  • A dataset of 131 patients with paired non-contrast and contrast-enhanced CT scans was used.
  • A U-net based deep learning model was trained for blood vessel segmentation on non-contrast CT.
  • Artery segmentations were generated and aligned with non-contrast CT scans.

Main Results:

  • The deep learning model achieved Dice coefficients of 0.638 on test data and 0.673 using cross-validation.
  • Successful segmentation of cerebral arteries on non-contrast CT scans was demonstrated.
  • The study validates the feasibility of generating angiographies without contrast administration.

Conclusions:

  • Deep learning effectively segments cerebral arteries on non-contrast CT, enabling contrast-free angiography.
  • This approach offers a valuable alternative for patients with contrast contraindications.
  • The publicly available code facilitates further development of AI tools in medical imaging.