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

Retinal ischemic perivascular lesions in cortical cerebral infarction: a comparison against controls.

Eye (London, England)·2026
Same author

Minimal Fibrinolysis After Acute Intracerebral Hemorrhage Undercuts the Mechanism of Tranexamic Acid.

Journal of the American Heart Association·2026
Same author

Investigating Structurally and Pigmentary Colored Featherworks via Noninvasive Methodologies.

ACS omega·2026
Same author

Radiomics-based Differentiation of Recurrent Brain Metastases from Treatment Effects: A Multi-Institutional Comparative Study with Advanced Imaging.

Radiology. Imaging cancer·2026
Same author

The Value of SSTR PET for Detection, Definition, and Ongoing Management of Meningioma.

Radiology·2026
Same author

Ophthalmic artery stenosis presenting as amaurosis fugax.

BMC ophthalmology·2026

Related Experiment Video

Updated: Jun 15, 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

42.5K

Precise Image-level Localization of Intracranial Hemorrhage on Head CT Scans with Deep Learning Models Trained on

Yunan Wu1, Michael Iorga1, Suvarna Badhe1

  • 1From the Departments of Electrical Computer Engineering (Y.W., S.L., A.A., A.K.K.) and Computer Science (A.K.K.), Northwestern University, Evanston, Ill; Departments of Radiology (M.I., S.B., D.R.C., N.S., M.D., T.A.H., E.J.R., T.B.P., A.K.K., V.B.H.) and Neurology (A.M.N.), Northwestern University Feinberg School of Medicine, 676 N St. Clair St, Ste 1400, Chicago, IL 60611; Shirley Ryan AbilityLab, Chicago, Ill (S.B.); Department of Radiology, Indiana University Health, Indianapolis, Ind (J.Z.); Department of Radiology, Medical College of Wisconsin, Milwaukee, Wis (E.J.T.); Department of Medical Imaging, McMaster University, Hamilton, Ontario, Canada, (S.T.H.); and Department of Radiology, Mount Sinai Medical Center, Miami Beach, Fla (K.M.P.).

Radiology. Artificial Intelligence
|August 28, 2024
PubMed
Summary

A new weakly supervised model can automatically detect intracranial hemorrhage (ICH) on CT scans using study-level labels. This AI tool shows high accuracy and generalizability, matching expert performance while significantly reducing diagnostic time.

Keywords:
Brain/Brain StemComputer-Aided Diagnosis (CAD)Convolutional Neural Network (CNN)HemorrhageTransfer Learning

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

47.9K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Related Experiment Videos

Last Updated: Jun 15, 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

42.5K
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

47.9K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Radiology
  • Neurology

Background:

  • Intracranial hemorrhage (ICH) detection on CT scans is critical for timely patient management.
  • Automated detection systems can aid radiologists, but often require extensive, pixel-level annotations.
  • Weakly supervised learning offers a potential solution by utilizing less granular labels.

Purpose of the Study:

  • To develop and validate a highly generalizable, weakly supervised model for automatic detection and localization of ICH.
  • To leverage study-level labels from radiology reports for training the model, reducing the need for detailed annotations.

Main Methods:

  • A retrospective study utilizing a weakly supervised model, pretrained on the RSNA dataset and fine-tuned on a local dataset.
  • The model employed attention-based bidirectional long short-term memory networks on 10,699 noncontrast head CT scans with study-level ICH labels.
  • Performance was evaluated against senior neuroradiologists on local and external test sets.

Main Results:

  • The model achieved a positive predictive value (PPV) of 85.7% on the local test set and 89.3% on the external test set.
  • Area under the ROC curve was 0.96 for both local and external test sets.
  • The model's diagnostic time (5.04 seconds) was significantly faster than neuroradiologists (86 and 22.2 seconds), with comparable performance.

Conclusions:

  • The developed weakly supervised model demonstrates high generalizability and accuracy for ICH detection.
  • The model offers a valuable tool for expedited ICH detection and prioritization in clinical workflows.
  • This approach can potentially reduce false-positive findings and improve radiologist efficiency.