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

Impaired axon regeneration and heightened synaptic dynamics in the injured aged mammalian cortex.

iScience·2025
Same author

PINNing cerebral blood flow: analysis of perfusion MRI in infants using physics-informed neural networks.

Frontiers in network physiology·2025
Same author

High-Resolution Maps of Left Atrial Displacements and Strains Estimated With 3D Cine MRI Using Online Learning Neural Networks.

IEEE transactions on medical imaging·2025
Same author

Quality assurance of late gadolinium enhancement cardiac magnetic resonance images: a deep learning classifier for confidence in the presence or absence of abnormality with potential to prompt real-time image optimization.

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance·2024
Same author

Aortic stenosis assessment from the 3-chamber cine: Ratio of balanced steady-state-free-precession (bSSFP) blood signal between the aorta and left ventricle predicts severity.

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance·2024
Same author

GSM-Net: A global sequence modelling network for the segmentation of short axis CINE MRI images.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2023

Related Experiment Video

Updated: Aug 16, 2025

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

9.0K

TMS-Net: A segmentation network coupled with a run-time quality control method for robust cardiac image segmentation.

Fatmatülzehra Uslu1, Anil A Bharath2

  • 1Bursa Technical University, Electrical and Electronics Engineering Department, Bursa, 16310, Turkey.

Computers in Biology and Medicine
|December 19, 2022
PubMed
Summary

This study introduces TMS-Net, a novel deep learning model for cardiac MRI segmentation. It enhances clinician trust by accurately predicting segmentation quality at runtime, improving diagnostic reliability.

Keywords:
Cardiac image analysisEngineered noiseRician noiseRobust image segmentationTrustworthiness

More Related Videos

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

2.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.1K

Related Experiment Videos

Last Updated: Aug 16, 2025

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

9.0K
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

2.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.1K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Cardiology

Background:

  • Deep networks excel at cardiac MRI segmentation but lack clinical trust due to robustness issues.
  • Runtime quality prediction is crucial for clinical adoption but is understudied.
  • Existing multi-view networks have limitations in noise robustness and quality estimation.

Purpose of the Study:

  • To develop a robust quality control method for cardiac MRI segmentation.
  • To enhance clinician trust in automated image analysis tools.
  • To improve the reliability of deep learning models in clinical settings.

Main Methods:

  • Proposed TMS-Net, a multi-view network with a single encoder and three decoders.
  • Utilized cosine similarity across decoders to measure agreement for quality estimation.
  • Generated synthetic noisy images to simulate segmentation challenges.
  • Evaluated on STACOM 2013 and STACOM 2018 datasets for left atrium segmentation.

Main Results:

  • TMS-Net demonstrated improved noise robustness and segmentation performance.
  • The quality estimation method achieved an AUC of 0.97 on the STACOM 2018 dataset.
  • The method effectively classified good and poor quality segmentation masks.

Conclusions:

  • TMS-Net offers a promising solution for reliable cardiac MRI segmentation.
  • Runtime quality prediction significantly enhances the trustworthiness of automated tools.
  • This approach has high potential to increase clinician confidence in AI-driven medical imaging analysis.