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

P-glycoprotein 1 as a shared target for resensitizing drug-resistant tumor cells and preventing fibronectin-driven metastasis.

Theranostics·2026
Same author

Complications of minimally invasive treatments of benign thyroid nodules: preventive andmanaging strategies: A systematic review.

La Radiologia medica·2026
Same author

Medication Adherence and Risks of Mortality and End-Organ Damage in Asian Patients with Type 2 Diabetes: A Cohort Study from Southern Taiwan.

Biomedicines·2026
Same author

Effect of Preoperative Transarterial Embolization on Surgical Blood Loss in Thyroidectomy for Large Graves' Disease.

World journal of surgery·2026
Same author

Thyroid function alterations after radiofrequency ablation in benign thyroid nodule management.

Therapeutic advances in endocrinology and metabolism·2026
Same author

International expert consensus on thermal ablation for benign thyroid nodules (2025 Edition).

International journal of surgery (London, England)·2026

Related Experiment Video

Updated: Oct 1, 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

48.5K

Toward automated segmentation for acute ischemic stroke using non-contrast computed tomography.

Shih-Yen Lin1, Pi-Ling Chiang2, Peng-Wen Chen3

  • 1Department of Computer Science, National Yang Ming Chiao Tung University, 1001 University Road, Hsinchu, Taiwan.

International Journal of Computer Assisted Radiology and Surgery
|March 8, 2022
PubMed
Summary

A new R2U-RNet model accurately segments acute ischemic stroke (AIS) lesions on non-contrast computed tomography (NCCT) scans. This AI tool aids in faster diagnosis and improved treatment for AIS patients.

Keywords:
Acute ischemic strokeDeep learningImage segmentationNon-contrast computed tomography

More Related Videos

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

1.8K
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

12.2K

Related Experiment Videos

Last Updated: Oct 1, 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

48.5K
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

1.8K
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

12.2K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neurology

Background:

  • Non-contrast computed tomography (NCCT) is crucial for acute ischemic stroke (AIS) treatment decisions.
  • NCCT's limited contrast and signal-to-noise ratio challenge accurate radiologist diagnosis and automated lesion segmentation.
  • Automated segmentation of AIS lesions on NCCT remains a significant hurdle in clinical practice.

Purpose of the Study:

  • Propose R2U-RNet, a novel deep learning model for enhanced AIS lesion segmentation using NCCT.
  • Improve the accuracy and efficiency of automated AIS lesion detection in clinical settings.

Main Methods:

  • Developed R2U-RNet based on an R2U-Net architecture with a residual refinement unit.
  • Utilized a retrospective NCCT dataset of 261 AIS patients with manual lesion segmentation.
  • Incorporated multiscale focal loss for class imbalance and a noisy-label training scheme for annotation uncertainty.

Main Results:

  • The R2U-RNet model significantly outperformed existing segmentation models in AIS lesion segmentation on NCCT.
  • Ablation studies confirmed the model's effectiveness and the contribution of its components.
  • Segmentation performance was influenced by stroke occurrence region and side, highlighting the need for region-specific information.

Conclusions:

  • R2U-RNet demonstrates significant potential for automated AIS lesion segmentation on NCCT.
  • The model can accelerate AIS diagnosis and enhance treatment quality for patients.
  • Future work may explore region-specific adaptations for improved segmentation accuracy.