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

Limbic System Microstructure in Neonates With Antenatal Opioid Exposure.

JAMA network open·2026
Same author

Diminished Late Gestation Placental Volume in Fetal Heart Disease and Implications for Birth Anthropometrics.

Journal of cardiovascular development and disease·2026
Same author

Perceived Control in the NICU: Implications for Maternal Mental Health and Parenting in the NICU.

Psychology research and behavior management·2026
Same author

Depressive Symptoms Associated with Decreased Choline Intake in Lactating Mothers of Preterm Infants.

Nutrients·2026
Same author

The developing relationship between circadian rhythm and heart rate variability in premature infants.

Clinical autonomic research : official journal of the Clinical Autonomic Research Society·2026
Same author

Antenatal Opioid Exposure and Cerebral Cortical Maturation in Newborns.

JAMA network open·2026

Related Experiment Video

Updated: Nov 8, 2025

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
08:49

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

Published on: August 1, 2022

3.9K

Image Quality Assessment of Fetal Brain MRI Using Multi-Instance Deep Learning Methods.

Axel Largent1, Kushal Kapse1, Scott D Barnett1

  • 1Developing Brain Institute, Division of Diagnostic Imaging and Radiology, Children's National Hospital, Washington, District of Columbia, USA.

Journal of Magnetic Resonance Imaging : JMRI
|April 23, 2021
PubMed
Summary
This summary is machine-generated.

Multi-instance count-based deep learning methods (DLMs) can automatically assess fetal MRI quality, improving upon subjective visual inspection. Incorporating gestational age further enhanced the performance of the best-performing DLM.

Keywords:
deep learningfetal brain MRIimage quality assessmentmulti-instance learningweakly supervised learning

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.3K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.5K

Related Experiment Videos

Last Updated: Nov 8, 2025

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
08:49

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

Published on: August 1, 2022

3.9K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.3K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.5K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Fetal Medicine

Background:

  • Fetal brain MRI quality varies due to fetal movement and maternal respiration.
  • Current quality assessment relies on time-consuming and subjective visual inspection.
  • Deep learning methods offer potential for automated quality assessment.

Purpose of the Study:

  • To develop and evaluate multi-instance deep learning methods (DLMs) for automatic 3D fetal brain MRI quality assessment.
  • To compare count-based, vote-based, and feature-embedding DLMs.
  • To investigate the impact of fetal gestational age (GA) on DLM performance.

Main Methods:

  • Retrospective analysis of 271 fetal brain MRI exams from 211 fetuses.
  • Development of three multi-instance DLMs: MI-CB-DLM, MI-VB-DLM, MI-FE-DLM.
  • Ground truth established by expert neuroradiologists, neuroscientist, and MRI technician.
  • Evaluation using 10-fold cross-validation, with GA included as a variable for some models.

Main Results:

  • The MI count-based DLM (MI-CB-DLM) demonstrated superior performance compared to other DLMs.
  • MI-CB-DLM achieved an average accuracy of 0.85 (without GA) and 0.86 (with GA).
  • Incorporating GA as an input to MI-CB-DLM improved its performance metrics.

Conclusions:

  • MI-CB-DLM is a promising method for objective and rapid assessment of fetal brain MRI quality.
  • Gestational age is a significant factor influencing DLM performance.
  • Automated DLM assessment can streamline the MRI acquisition process.