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

Inflammatory protein mediators linking gut microbiota to degenerative lumbar spine disorders: cross-disease genetic evidence.

Frontiers in immunology·2026
Same author

Subthalamic segmentations in relation to deep brain stimulation volumes in Parkinson's disease.

Acta neurochirurgica·2026
Same author

Automated perfusion imaging did not improve reliability of ASPECTS or collateral score in late-window large vessel occlusion stroke.

Journal of neurointerventional surgery·2026
Same author

Deep learning-based femoral reconstruction from intraoperative point clouds for enhanced knee arthroplasty registration.

International journal of computer assisted radiology and surgery·2026
Same author

Electron Irradiation Effects on N and Fe<sup>3+</sup> Doped Carbon Dots and the Application in Radiotherapy of Lung Cancer.

International journal of nanomedicine·2026
Same author

Characterizing forearm skeletal muscle composition and function in breast cancer-related lymphedema using B-mode ultrasonography.

Clinical physiology and functional imaging·2026
Same journal

ESD-VesNet: uncertainty-aware vessel segmentation network for endoscopic submucosal dissection with hard negative mining.

International journal of computer assisted radiology and surgery·2026
Same journal

Lean Unet: a compact model for image segmentation.

International journal of computer assisted radiology and surgery·2026
Same journal

Strain alignment: toward assessing mechanical plausibility of predicted displacement fields.

International journal of computer assisted radiology and surgery·2026
Same journal

Vascular geometry characterization for AI-based endovascular navigation.

International journal of computer assisted radiology and surgery·2026
Same journal

Nail It! A learning framework for autonomous surgical suturing and teleoperation on the dVRK.

International journal of computer assisted radiology and surgery·2026
Same journal

Correspondence-free local-to-global liver deformation correction via implicit neural representation and biomechanical model.

International journal of computer assisted radiology and surgery·2026
See all related articles

Related Experiment Video

Updated: Aug 14, 2025

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

48.2K

Deep learning for collateral evaluation in ischemic stroke with imbalanced data.

Mumu Aktar1, Jonatan Reyes2, Donatella Tampieri3

  • 1Computer Science and Software Engineering, Concordia University, 1455 boul. De Maisonneuve O., Montreal, QC, H3G 1M8, Canada. m_ktar@encs.concordia.ca.

International Journal of Computer Assisted Radiology and Surgery
|January 12, 2023
PubMed
Summary
This summary is machine-generated.

This study developed an automated deep learning method for assessing cerebral collateral status in ischemic stroke patients. The approach improves accuracy and consistency, aiding treatment decisions.

Keywords:
4D CTACollateral evaluationEfficientNet B0Ischemic strokeMajority votingTransfer learning

More Related Videos

A Fibrin-Enriched and tPA-Sensitive Photothrombotic Stroke Model
09:42

A Fibrin-Enriched and tPA-Sensitive Photothrombotic Stroke Model

Published on: June 4, 2021

2.8K
Focal Cerebral Ischemia Model by Endovascular Suture Occlusion of the Middle Cerebral Artery in the Rat
13:50

Focal Cerebral Ischemia Model by Endovascular Suture Occlusion of the Middle Cerebral Artery in the Rat

Published on: February 5, 2011

80.0K

Related Experiment Videos

Last Updated: Aug 14, 2025

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

48.2K
A Fibrin-Enriched and tPA-Sensitive Photothrombotic Stroke Model
09:42

A Fibrin-Enriched and tPA-Sensitive Photothrombotic Stroke Model

Published on: June 4, 2021

2.8K
Focal Cerebral Ischemia Model by Endovascular Suture Occlusion of the Middle Cerebral Artery in the Rat
13:50

Focal Cerebral Ischemia Model by Endovascular Suture Occlusion of the Middle Cerebral Artery in the Rat

Published on: February 5, 2011

80.0K

Area of Science:

  • Medical Imaging Analysis
  • Artificial Intelligence in Healthcare
  • Neurology

Background:

  • Cerebral collateral assessment in ischemic stroke is crucial for treatment decisions but relies on subjective visual inspection, leading to variability.
  • Limited availability of large, open-access datasets of ischemic stroke patients hinders the development of advanced computational methods like deep learning.

Purpose of the Study:

  • To develop an automated and robust method for evaluating cerebral collateral status in ischemic stroke patients.
  • To overcome limitations of manual collateral assessment, including inter- and intra-rater variability.
  • To address challenges posed by small and imbalanced datasets in deep learning applications for stroke imaging.

Main Methods:

  • Adapted a pre-trained EfficientNet B0 network using transfer learning for slice-based and subject-level collateral classification.
  • Employed a stacking and overlapping strategy for 2D slices from 4D computed tomography angiography (CTA) data.
  • Utilized a majority voting scheme for final collateral grading and focal loss with class weighting to handle data imbalance.

Main Results:

  • Achieved a weighted F1 score of 0.71 for multi-class (good, intermediate, poor) collateral classification (sensitivity 0.71, specificity 0.84).
  • Demonstrated high performance in a dichotomized classification (good/intermediate vs. poor) for treatment decisions, yielding a weighted F1 score of 0.95 (sensitivity 0.89, specificity 0.96).
  • Validated the method using nine-fold cross-validation on 83 subjects.

Conclusions:

  • Developed an automatic and robust collateral assessment tool, mitigating issues associated with small, imbalanced datasets.
  • The computer-aided evaluation system shows potential to assist clinicians in making informed decisions regarding ischemic stroke treatment strategies.
  • This approach can enhance consistency and accuracy in collateral assessment, improving patient care.