Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Imaging Studies for Cardiovascular System V: CT

Imaging Studies for Cardiovascular System V: CT

Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Digital health determinants & divide in the Arab world: A cross-sectional study.

PloS one·2025

Same author

A structural equation modeling approach to examine determinants of nutritional status in Palestinian children 6-59 months.

PloS one·2025

Same author

Determinants of Child Growth in Palestine (Ages 5-17): A Structural Equation Modeling Approach to Food Insecurity, Nutrition, and Socioeconomic Factors.

Children (Basel, Switzerland)·2025

Same author

Machine Learning Approach for Predicting the Impact of Food Insecurity on Nutrient Consumption and Malnutrition in Children Aged 6 Months to 5 Years.

Children (Basel, Switzerland)·2024

Same author

Hybrid Ensemble Deep Learning Model for Advancing Ischemic Brain Stroke Detection and Classification in Clinical Application.

Journal of imaging·2024

Same author

Investigating the Association between Nutrient Intake and Food Insecurity among Children and Adolescents in Palestine Using Machine Learning Techniques.

Children (Basel, Switzerland)·2024

Search research articles

Related Experiment Video

Updated: Jan 7, 2026

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

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

Published on: September 16, 2017

Optimized Hounsfield Units Transformation for Explainable Temporal Stage-Specific Ischemic Stroke Classification in

Radwan Qasrawi^1,2, Suliman Thwib¹, Ghada Issa¹

¹Department of Computer Science, Al Quds University, Jerusalem P.O. Box 20002, Palestine.

Journal of Imaging

|December 24, 2025

Summary

A novel neural network framework dynamically optimizes CT image enhancement for accurate ischemic stroke classification. This method significantly improves detection across all stroke stages compared to static approaches.

Keywords:

computed tomography explainable AI hounsfield unit image enhancement ischemic stroke neural networks

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

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

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

Published on: June 2, 2023

Related Experiment Videos

Last Updated: Jan 7, 2026

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

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

Published on: September 16, 2017

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

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

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

Published on: June 2, 2023

Area of Science:

Medical Imaging
Artificial Intelligence in Medicine
Neurology

Background:

Accurate ischemic stroke classification on CT is challenging due to subtle image differences and scanner variability.
Early detection is crucial for effective treatment and patient outcomes.

Purpose of the Study:

To develop and validate a neural network framework for dynamic optimization of CT image enhancement parameters.
To achieve stage-specific classification of ischemic stroke (hyperacute, acute, subacute, chronic).

Main Methods:

A convolutional neural network (CNN) optimized Hounsfield Unit (HU) transformations and CLAHE parameters.
Training data included 1480 CT cases across five stages, with augmentation.
Classifiers (LR, SVM, RF) were used with 25-fold cross-validation; interpretability assessed via Grad-CAM.

Main Results:

The optimized framework significantly outperformed static parameters in accuracy for all stroke stages.
Deep CLAHE achieved higher accuracies (e.g., 0.9979 for chronic) than static CLAHE.
Model interpretability confirmed focus on clinically relevant regions, with stage-aware parameter adaptation.

Conclusions:

A neural network-optimized framework offers superior, stage-specific ischemic stroke classification.
The interpretability validation and pathophysiology-aligned adaptation provide a transparent and clinically viable solution.
This approach enhances emergency stroke assessment accuracy and efficiency.