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

Research on Three-Dimensional Reconstruction of Ribs Based on Point Cloud Adaptive Smoothing Denoising.

Sensors (Basel, Switzerland)·2024
Same author

Domain adaptation via Wasserstein distance and discrepancy metric for chest X-ray image classification.

Scientific reports·2024
Same author

Multi-Branch Attention Learning for Bone Age Assessment with Ambiguous Label.

Sensors (Basel, Switzerland)·2023
Same author

Wireless Phone Use and Risk of Adult Glioma: Evidence from a Meta-Analysis.

World neurosurgery·2018
Same author

Progressive cystic lesion in a middle-aged patient with tuberous sclerosis complex: A case report.

Medicine·2018
Same author

The focal alteration and causal connectivity in children with new-onset benign epilepsy with centrotemporal spikes.

Scientific reports·2018

Related Experiment Video

Updated: Jun 26, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K

Deep multiscale convolutional feature learning for intracranial hemorrhage classification and weakly supervised

Bishi He1, Zhe Xu1, Dong Zhou1

  • 1School of Automation (School of Artificial Intelligence), Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China.

Heliyon
|May 9, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces an AI model for detecting and locating brain bleeds using CT scans. The model accurately classifies intracerebral hemorrhage subtypes, significantly improving diagnostic speed in emergencies.

Keywords:
Deep learningIntracranial hemorrhageIntraparenchymalIntraventricularSubarachnoid

More Related Videos

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

48.0K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.2K

Related Experiment Videos

Last Updated: Jun 26, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K
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

48.0K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.2K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Intracerebral hemorrhage (ICH) diagnosis relies on expert interpretation of CT scans.
  • Accurate and timely localization of bleeding is crucial for effective patient management.
  • Current diagnostic workflows can be time-consuming, especially in emergency settings.

Purpose of the Study:

  • To evaluate an AI model for classifying ICH and localizing bleeding foci using multiscale features and attentional fusion.
  • To assess the model's performance on a large dataset of brain CT scans.
  • To determine if the model can aid in reducing diagnostic time and improving ICH detection.

Main Methods:

  • Utilized a large dataset of 750,000 brain CT scans from the ASNR.
  • Developed a framework employing attentional fusion and multiscale features for classification and weakly supervised localization.
  • The model was trained and validated for ICH classification and subtype identification.

Main Results:

  • Achieved high performance in ICH classification (AUC=0.973) and localization.
  • Demonstrated excellent AUC values for specific hemorrhage subtypes: epidural (0.891), subdural (0.991), subarachnoid (0.983), intraventricular (0.995), and intraparenchymal (0.990).
  • Outperformed average entry-level radiology trainees in accuracy based on prior data.

Conclusions:

  • The developed AI framework accurately detects and classifies ICH subtypes using only image-level annotations.
  • The method significantly reduces diagnostic time and enhances ICH detection in emergency scenarios.
  • This AI tool shows potential for integration into future diagnostic radiology workflows.