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: Jul 5, 2025

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.5K

Temporal Uncertainty Localization to Enable Human-in-the-Loop Analysis of Dynamic Contrast-Enhanced Cardiac MRI

Dilek M Yalcinkaya1,2, Khalid Youssef1,3, Bobak Heydari4

  • 1Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine (IUSM), Indianapolis, IN, USA.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|January 11, 2024
PubMed
Summary

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

Cardiac MRI of Chronic Myocardial Infarction: Emergence of a New Era?

Journal of the American College of Cardiology·2026
Same author

The importance of spatial resolution in detecting chronic myocardial iron remnants following hemorrhagic myocardial infarction with T2* MRI.

Biomedical physics & engineering express·2026
Same author

Filling the Gaps: Generating 4D Dense Cardiac Anatomy from Sparse CMR for Enhanced Tetralogy of Fallot Assessment.

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance·2026
Same author

Modeling Aleatoric Uncertainty in Cardiac MRI Segmentation: Probabilistic Detection and Contour Regression.

IEEE transactions on medical imaging·2026
Same author

Predicting Intramyocardial Hemorrhage Before Reperfusion in STEMI Patients With Intrinsically Explainable Artificial Intelligence.

JACC. Advances·2026
Same author

Ferumoxytol-Enhanced Myocardial T1 Tracking Using a Hybrid 2D/3D Steady-State MRI Sequence Captures Cyclic Intramyocardial Blood Volume Dynamics.

NMR in biomedicine·2026

A new dynamic quality control (dQC) method improves deep neural network (DNN) segmentation for dynamic contrast-enhanced cardiac MRI (DCE-CMRI) by identifying uncertain image segments. This reduces failed segmentations and enhances diagnostic accuracy for myocardial perfusion.

Area of Science:

  • Medical Imaging
  • Cardiovascular Imaging
  • Artificial Intelligence in Medicine

Background:

  • Dynamic contrast-enhanced cardiac magnetic resonance imaging (DCE-CMRI) is crucial for diagnosing myocardial perfusion abnormalities.
  • Acquiring numerous images in DCE-CMRI makes manual segmentation time-consuming and prone to errors, especially with motion artifacts.
  • Deep neural networks (DNNs) show potential for DCE-CMRI analysis, but lack robust quality control for segmentation failures.

Purpose of the Study:

  • To develop and validate a novel space-time uncertainty metric for dynamic quality control (dQC) of DNN-based segmentation in free-breathing DCE-CMRI.
  • To establish a human-in-the-loop framework utilizing the dQC metric to refine segmentation results and improve diagnostic accuracy.
  • To assess the efficiency and effectiveness of the proposed dQC approach compared to random selection for human review.
Keywords:
Cardiovascular MRIDynamic MRIHuman-in-the-loop A.I.Image SegmentationQuality controlUncertainty Quantification

More Related Videos

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

291
Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET
09:03

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET

Published on: October 22, 2019

10.0K

Related Experiment Videos

Last Updated: Jul 5, 2025

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.5K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

291
Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET
09:03

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET

Published on: October 22, 2019

10.0K

Main Methods:

  • Proposed a space-time uncertainty metric to identify uncertain segmentations in DNN-based DCE-CMRI analysis.
  • Implemented a human-in-the-loop system referring the top 10% most uncertain segmentations for expert refinement.
  • Validated the approach on an external dataset and compared it against random selection for human review.

Main Results:

  • The dQC framework significantly increased the Dice score (p < 0.001), indicating improved segmentation accuracy.
  • The number of images with failed segmentations decreased from 16.2% to 11.3% using the dQC-guided approach.
  • Randomly selecting segmentations for human review did not yield significant improvements in segmentation quality.

Conclusions:

  • The proposed dQC framework effectively identifies poor-quality segmentations in DNN-based DCE-CMRI analysis.
  • This approach enables efficient, human-in-the-loop analysis of dynamic CMRI datasets, improving clinical interpretation.
  • The dQC tool has the potential to enhance the reliability and efficiency of automated analysis for dynamic cardiac MRI.