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

  1. Home
  3. Research Domains
  5. Information And Computing Sciences
  7. Artificial Intelligence
  9. Natural Language Processing
  11. Automated Ischemic Stroke Lesion Detection On Non-contrast Brain Ct: A Large-scale Clinical Feasibility Test Ai Stroke Lesion Detection On Ncct.
  1. Home
  3. Research Domains
  5. Information And Computing Sciences
  7. Artificial Intelligence
  9. Natural Language Processing
  11. Automated Ischemic Stroke Lesion Detection On Non-contrast Brain Ct: A Large-scale Clinical Feasibility Test Ai Stroke Lesion Detection On Ncct.

Related Experiment Video

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

49.3K

Automated ischemic stroke lesion detection on non-contrast brain CT: a large-scale clinical feasibility test AI stroke lesion detection on NCCT.

JoonNyung Heo1, Wi-Sun Ryu2, Jong-Won Chung3

  • 1Department of Neurology, Yonsei University College of Medicine, Seoul, Republic of Korea.

Frontiers in Neuroscience
|September 11, 2025

View abstract on PubMed

Summary
This summary is machine-generated.

An automated software for detecting ischemic lesions on non-contrast CT (NCCT) shows promise for acute stroke imaging. This tool aids in identifying subtle changes and predicting outcomes in patients undergoing endovascular thrombectomy.

Keywords:
artificial intelligencebrain CTischemic strokenon-contrast CT

More Related Videos

Optimized Management of Endovascular Treatment for Acute Ischemic Stroke
09:21

Optimized Management of Endovascular Treatment for Acute Ischemic Stroke

Published on: January 18, 2018

12.5K
Combined Near-infrared Fluorescent Imaging and Micro-computed Tomography for Directly Visualizing Cerebral Thromboemboli
13:10

Combined Near-infrared Fluorescent Imaging and Micro-computed Tomography for Directly Visualizing Cerebral Thromboemboli

Published on: September 25, 2016

10.3K

Related Experiment Videos

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

49.3K
Optimized Management of Endovascular Treatment for Acute Ischemic Stroke
09:21

Optimized Management of Endovascular Treatment for Acute Ischemic Stroke

Published on: January 18, 2018

12.5K
Combined Near-infrared Fluorescent Imaging and Micro-computed Tomography for Directly Visualizing Cerebral Thromboemboli
13:10

Combined Near-infrared Fluorescent Imaging and Micro-computed Tomography for Directly Visualizing Cerebral Thromboemboli

Published on: September 25, 2016

10.3K

Area of Science:

  • Neurology
  • Radiology
  • Medical Imaging

Background:

  • Non-contrast CT (NCCT) is a standard imaging technique for acute stroke.
  • NCCT often fails to detect early ischemic changes, potentially leading to missed diagnostic information.
  • Early detection of ischemic lesions is crucial for timely and effective stroke treatment.

Purpose of the Study:

  • To develop and externally validate automated software for detecting ischemic lesions on NCCT.
  • To assess the clinical feasibility of this automated software in stroke patients.
  • To evaluate the software's ability to provide prognostic information in endovascular thrombectomy patients.

Main Methods:

  • A modified 3D U-Net model was trained on paired NCCT and diffusion-weighted imaging (DWI) data from 2,214 acute ischemic stroke patients.
stroke - diagnosis
  • External validation was conducted on 458 subjects, and clinical feasibility was assessed in 603 endovascular thrombectomy patients.
  • Model performance was evaluated against expert annotations for sensitivity, specificity, and volumetric correlation, with clinical endpoints including lesion volume and outcomes.

    • Main Results:

    • The automated NCCT lesion detection model achieved 75.3% sensitivity and 79.1% specificity in external validation.
    • NCCT-derived lesion volumes correlated with follow-up DWI volumes (ρ=0.60, p<0.001).
    • Larger lesions (>50 mL) were linked to poorer outcomes and increased hemorrhagic transformation, while radiomics features improved prediction accuracy.

    Conclusions:

    • Automated NCCT-based lesion detection software demonstrates reliable diagnostic performance for acute ischemic stroke.
    • The software provides clinically relevant prognostic information, particularly for patients undergoing endovascular thrombectomy.
    • This technology has the potential to improve the management of acute stroke by enhancing early lesion detection and outcome prediction.