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

Navigating the Complexity and Heterogeneity of Thrombectomy Decision-Making for Medium-Vessel Occlusion Stroke: Where Do We Go From Here?

Stroke (Hoboken, N.J.)·2026
Same author

Human Rights as Justifications in Wildernesses: A Third World Approach to EU Law.

Jus cogens·2026
Same author

Sex differences in brain frailty measures and outcomes after endovascular thrombectomy: ESCAPE-NA1 analysis.

Journal of the neurological sciences·2026
Same author

Effects of Environmental Arsenic Exposure on the Morphology of Multiple Organs in Female Mice During Pre-Pregnancy, Gestation, and Lactation.

Journal of applied toxicology : JAT·2026
Same author

Patient-physician familiarity is just as important for virtual outpatient encounters as for in-person encounters: a retrospective cohort study.

Scientific reports·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

Related Experiment Video

Updated: May 10, 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

47.7K

Synchronous Image-Label Diffusion Probability Model With Application to Stroke Lesion Segmentation on Non-Contrast

Jianhai Zhang, Tonghua Wan, M Ethan MacDonald

    IEEE Transactions on Neural Networks and Learning Systems
    |April 22, 2025
    PubMed
    Summary

    This study introduces a novel Synchronous Image-Label Diffusion Probability Model (SDPM) for accurate stroke lesion segmentation on noncontrast CT scans. The SDPM achieves state-of-the-art results, improving prognosis assessment for acute ischemic stroke patients.

    More Related Videos

    A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia
    09:59

    A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia

    Published on: September 16, 2017

    14.0K
    Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke
    06:45

    Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke

    Published on: June 2, 2023

    1.2K

    Related Experiment Videos

    Last Updated: May 10, 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

    47.7K
    A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia
    09:59

    A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia

    Published on: September 16, 2017

    14.0K
    Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke
    06:45

    Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke

    Published on: June 2, 2023

    1.2K

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Radiology

    Background:

    • Accurate stroke lesion volume measurement is crucial for acute ischemic stroke (AIS) prognosis.
    • Automatic lesion segmentation on noncontrast CT (NCCT) remains challenging.
    • Diffusion probabilistic models (DPMs) show promise for medical image segmentation.

    Purpose of the Study:

    • To propose a novel Synchronous Image-Label Diffusion Probability Model (SDPM) for stroke lesion segmentation on NCCT.
    • To leverage generative latent variable models (LVMs) for probabilistic lesion segmentation.
    • To develop a flexible and accurate segmentation method for AIS patients.

    Main Methods:

    • Introduced a novel SDPM utilizing a dual-Markov diffusion process with shared noise.
    • Developed a network architecture with parallel noise prediction and net-streams for label estimation.
    • Implemented four label-inference methods for flexible segmentation at various time scales.
    • Trained and validated the model on public and private stroke lesion datasets.

    Main Results:

    • The SDPM achieved state-of-the-art accuracy in stroke lesion segmentation.
    • Outperformed existing U-Net, transformer, and DPM-based segmentation methods.
    • Demonstrated flexibility in inferring final labels using multiple methods.

    Conclusions:

    • The proposed SDPM offers a robust and accurate solution for automatic stroke lesion segmentation on NCCT.
    • This advancement can improve the prognostic assessment of AIS patients.
    • SDPM represents a significant step forward in applying generative models to medical image analysis.