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

Quality of life after tranexamic acid in subarachnoid hemorrhage: post-hoc analysis of the ULTRA trial.

Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation·2026
Same author

Mapping the mRS Into the EQ-5D-5L in Patients With Ischemic Stroke.

Stroke·2026
Same author

Temporal Net Water Uptake Evolution and its Association with Functional Outcome in Acute Ischemic Stroke.

AJNR. American journal of neuroradiology·2026
Same author

CTP-Free Method for Automated Lesion Water Uptake in Acute Ischemic Stroke.

AJNR. American journal of neuroradiology·2026
Same author

Validation and simplification of the MR PREDICTS @24H model for outcome prediction after endovascular thrombectomy for acute ischemic stroke.

International journal of stroke : official journal of the International Stroke Society·2026
Same author

Association of CRP levels and clinical and radiological outcomes in patients with large-vessel occlusion stroke: A MR CLEAN Registry study.

European stroke journal·2026

Related Experiment Video

Updated: Aug 11, 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

PerfU-Net: Baseline infarct estimation from CT perfusion source data for acute ischemic stroke.

Lucas de Vries1, Bart J Emmer2, Charles B L M Majoie2

  • 1Amsterdam UMC, Department of Radiology and Nuclear Medicine, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands; Amsterdam UMC, Department of Biomedical Engineering and Physics, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands; University of Amsterdam, Informatics Institute, Science Park 900, Amsterdam, 1098 XH, The Netherlands.

Medical Image Analysis
|February 2, 2023
PubMed
Summary

This study introduces a machine learning model for infarct core segmentation in acute ischemic stroke patients directly from CT perfusion source data. The novel approach minimizes discrepancies from standard software, improving accuracy in stroke lesion assessment.

Keywords:
Acute ischemic strokeCT perfusionInfarct core segmentationSpatio-temporal attention U-net

More Related Videos

In Vivo Quantitative Assessment of Myocardial Structure, Function, Perfusion and Viability Using Cardiac Micro-computed Tomography
08:13

In Vivo Quantitative Assessment of Myocardial Structure, Function, Perfusion and Viability Using Cardiac Micro-computed Tomography

Published on: February 16, 2016

19.7K
Optimized System for Cerebral Perfusion Monitoring in the Rat Stroke Model of Intraluminal Middle Cerebral Artery Occlusion
12:15

Optimized System for Cerebral Perfusion Monitoring in the Rat Stroke Model of Intraluminal Middle Cerebral Artery Occlusion

Published on: February 17, 2013

23.3K

Related Experiment Videos

Last Updated: Aug 11, 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
In Vivo Quantitative Assessment of Myocardial Structure, Function, Perfusion and Viability Using Cardiac Micro-computed Tomography
08:13

In Vivo Quantitative Assessment of Myocardial Structure, Function, Perfusion and Viability Using Cardiac Micro-computed Tomography

Published on: February 16, 2016

19.7K
Optimized System for Cerebral Perfusion Monitoring in the Rat Stroke Model of Intraluminal Middle Cerebral Artery Occlusion
12:15

Optimized System for Cerebral Perfusion Monitoring in the Rat Stroke Model of Intraluminal Middle Cerebral Artery Occlusion

Published on: February 17, 2013

23.3K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neurology

Background:

  • CT perfusion imaging is crucial for quantifying infarct cores in acute ischemic stroke.
  • Existing CT perfusion software exhibits significant vendor-specific discrepancies in outcomes and perfusion maps.
  • Accurate infarct core segmentation is vital for effective stroke treatment.

Purpose of the Study:

  • To develop a machine learning model for direct infarct core segmentation from CT perfusion source data.
  • To overcome the limitations and vendor variability associated with standard CT perfusion software.
  • To improve the accuracy and reliability of infarct core assessment in acute ischemic stroke.

Main Methods:

  • A symmetry-aware spatio-temporal segmentation model (PerfU-Net) was developed.
  • The model encodes brain micro-perfusion dynamics and decodes a static segmentation map.
  • An attention module was incorporated into skip-connections for improved encoder-decoder dimension matching.

Main Results:

  • The PerfU-Net achieved state-of-the-art results (Dice score 0.46) using only CT perfusion source data.
  • Performance was comparable to methods relying on variable third-party perfusion maps.
  • The model outperformed simple perfusion map analysis used in clinical practice.

Conclusions:

  • Direct segmentation from CT perfusion source data using machine learning is a viable alternative to standard software.
  • The proposed spatio-temporal model offers improved accuracy and consistency in infarct core quantification.
  • This approach has the potential to enhance clinical decision-making for acute ischemic stroke patients.