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 Experiment Video

Updated: Jun 26, 2026

MRI and PET in Mouse Models of Myocardial Infarction
10:46

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

Association of Deep Learning-based Myocardial Infarction Size Quantification in Cardiac MRI with Cardiac Biomarker

Matthias Schwab1, Mathias Pamminger1, Christian Kremser1

  • 1University Clinic of Radiology, Medical University of Innsbruck, Anichstraße 35, 6020 Innsbruck, Austria.

Radiology. Cardiothoracic Imaging
|June 25, 2026
PubMed
Summary

Related Concept Videos

Imaging Studies for Cardiovascular System IV: CMRI01:21

Imaging Studies for Cardiovascular System IV: CMRI

Cardiovascular magnetic resonance imaging, or CMRI, is a non-invasive diagnostic test that employs a magnetic field and radiofrequency waves to create precise images of the heart and arteries. It provides comprehensive information about cardiac anatomy, function, perfusion, and tissue characterization without ionizing radiation.IndicationsCMRI diagnoses various heart conditions, including tissue damage from heart attacks, ischemic heart disease, myocarditis, aortic issues (tears, aneurysms,...

You might also read

Related Articles

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

Sort by
Same author

EACVI 2025: the full spectrum of cardiovascular imaging.

European heart journal·2026
Same author

DARE: A Deformable Adaptive Regularization Estimator for learning-based medical image registration.

Artificial intelligence in medicine·2026
Same author

Coronary Culprit Lesion Location and Intramyocardial Hemorrhage in STEMI.

Circulation. Cardiovascular imaging·2026
Same author

Smoking cessation after first STEMI enhances infarct healing: a cardiac MRI study.

European heart journal. Cardiovascular Imaging·2026
Same author

Deep Learning Framework for Automated MRI Planimetry in Multiple Sclerosis.

International journal of biomedical imaging·2026
Same author

Reduced right/left ventricular blood pool T2-ratio predicts congestive heart failure after STEMI.

Clinical research in cardiology : official journal of the German Cardiac Society·2026

An AI-based method for quantifying infarct size using cardiac MRI is reliable and clinically applicable. This artificial intelligence (AI) tool shows strong correlation with cardiac biomarkers and is comparable to manual measurements for ST-elevation myocardial infarction (STEMI) patients.

Area of Science:

  • Cardiovascular Imaging
  • Artificial Intelligence in Medicine
  • Cardiac MRI

Background:

  • Accurate quantification of infarct size in ST-elevation myocardial infarction (STEMI) is crucial for patient management.
  • Manual segmentation of infarcts on cardiac MRI is time-consuming and subject to inter-observer variability.
  • Artificial intelligence (AI) offers potential for automated and reliable image analysis.

Purpose of the Study:

  • To evaluate the reliability and clinical applicability of an AI-based infarct size quantification method using cardiac MRI.
  • To compare AI-derived infarct size measurements with manual segmentations in STEMI patients.
  • To assess the correlation of AI-based measurements with cardiac biomarkers and their predictive value for left ventricular adverse remodeling (LVAR).

Main Methods:

Keywords:
CardiacCardiac BiomarkersConvolutional Neural NetworksHeartIschemia/InfarctionLate Gadolinium EnhancementMR-ImagingST Elevation Myocardial InfarctionSegmentation

Related Experiment Videos

Last Updated: Jun 26, 2026

MRI and PET in Mouse Models of Myocardial Infarction
10:46

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

  • Retrospective study of STEMI patients who underwent cardiac MRI.
  • A convolutional neural network (CNN) was trained on manually segmented cardiac MRI examinations.
  • Infarct sizes were quantified using both manual segmentation and the trained CNN on a test set.
  • Correlations with peak creatine kinase (CK) and cardiac troponin T (cTnT) levels were analyzed.
  • Predictive value for LVAR was compared between manual and AI-based measurements.

Main Results:

  • The AI-based method estimated a larger median infarct size compared to manual measurements (26.5 mL vs 20.1 mL, P < .001).
  • AI-derived measurements showed a stronger correlation with peak CK (r = 0.76, ρ = 0.80) and cTnT (r = 0.66) levels than manual segmentations.
  • Both manual and AI-based measurements demonstrated comparable predictive value for LVAR (P = .24).

Conclusions:

  • The AI-based infarct size quantification method using cardiac MRI is reliable and clinically applicable.
  • The AI method is strongly correlated with cardiac biomarkers and comparable to manual measurements for STEMI patients.
  • This AI tool has the potential to streamline infarct size assessment in clinical practice.