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

Computational modelling for personalized transcatheter aortic valve replacement planning: a systematic review of complications and decision support.

Frontiers in digital health·2026
Same author

Accuracy and homogeneity of dictionary-based T2-mapping dedicated to single slice and multi-slice multi-echo turbo-spin echo imaging.

Magnetic resonance imaging·2026
Same author

Real-world insights into coronary CTA prognostication: value of semiquantitative scores.

La Radiologia medica·2026
Same author

Risks of automation in medicine - a review article for the obstetrics case.

Danish medical journal·2026
Same author

Gastric Volumetric Filling Capacity Before and After Sleeve Gastrectomy: a Magnetic Resonance Imaging and Biomechanical Study.

Obesity surgery·2026
Same author

DyABD: the abdominal muscle segmentation in dynamic MRI benchmark.

BMC medical imaging·2026

Related Experiment Video

Updated: Oct 22, 2025

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

3.0K

Medical image segmentation automatic quality control: A multi-dimensional approach.

Joris Fournel1, Axel Bartoli2, David Bendahan3

  • 1C.N.R.S., C.R.M.B.M., Medical Faculty, Aix-Marseille University, 27, Boulevard Jean Moulin, 13385 Marseille Cedex 05, France; Aix Marseille Univ, CNRS, I2M, Marseille, France.

Medical Image Analysis
|August 29, 2021
PubMed
Summary
This summary is machine-generated.

A new 2D deep learning method enhances cardiovascular MR image segmentation quality control. It outperforms 3D methods, improving accuracy for structures like the left ventricle myocardium and blood pool.

Keywords:
CMR Image segmentationDeep learningMedical image segmentation automatic quality controlMulti-dimensional quality control

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

576
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.1K

Related Experiment Videos

Last Updated: Oct 22, 2025

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

3.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

576
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.1K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Cardiovascular Imaging

Background:

  • Accurate medical image segmentation is critical for clinical decisions.
  • Existing automatic quality control methods for segmentation lack slice-level (2D) evaluation, leading to suboptimal performance.
  • Cardiovascular MR image segmentation errors can have serious clinical consequences.

Purpose of the Study:

  • To develop and evaluate a novel 2D-based deep learning method for simultaneous 2D and 3D quality control of cardiovascular MR image segmentations.
  • To compare the performance of the 2D-based method against traditional 3D approaches.

Main Methods:

  • A 2D deep learning model was trained to predict Dice Similarity Coefficients (DSC) for left ventricle structures (trabeculations, myocardium, papillary muscles, blood).
  • The 2D method was trained on 36,540 samples and compared against a 3D method trained on 3842 samples.
  • Performance was evaluated using Mean Absolute Errors (MAEs) at both 2D and 3D levels and validated against expert cardiologists' scores on UK BioBank data.

Main Results:

  • The 2D-based method demonstrated superior performance compared to the 3D method.
  • Low MAEs were achieved for DSC predictions at the 2D-level (0.02-0.05) and 3D-level (0.01-0.04) across different structures.
  • Clinical validation on 1016 subjects showed strong agreement with expert assessments.

Conclusions:

  • The proposed 2D deep learning approach effectively performs multi-level quality control for cardiovascular MR image segmentations.
  • This method offers improved accuracy and reliability over existing 3D techniques.
  • Multi-level quality control can enhance clinical measurements derived from medical image segmentations.