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

Imaging Studies III: Computed Tomography01:27

Imaging Studies III: Computed Tomography

33
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
33
Imaging Studies I: CT and MRI01:14

Imaging Studies I: CT and MRI

366
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
366
Computed Tomography01:10

Computed Tomography

4.7K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
4.7K

You might also read

Related Articles

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

Sort by
Same author

Artificial Intelligence as an Add-On Instrument in Fetal Ultrasound; Sonographers' and Obstetricians' Expectations.

Prenatal diagnosis·2026
Same author

From Bytes to Beats: Overcoming Conceptual and Implementation Challenges for AI in Cardiovascular Care.

Circulation·2025
Same author

X-Factor: Quality Is a Dataset-Intrinsic Property.

ArXiv·2025
Same author

Epistasis regulates genetic control of cardiac hypertrophy.

Nature cardiovascular research·2025
Same author

Self-supervised learning for label-free segmentation in cardiac ultrasound.

Nature communications·2025
Same author

The MI-CLAIM-GEN checklist for generative artificial intelligence in health.

Nature medicine·2025

Related Experiment Video

Updated: Aug 6, 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

2.8K

Domain-guided data augmentation for deep learning on medical imaging.

Chinmayee Athalye1, Rima Arnaout2

  • 1Division of Cardiology, Department of Medicine, Bakar Computational Health Sciences Institute, University of California San Francisco, San Francisco, California, United States of America.

Plos One
|March 23, 2023
PubMed
Summary

Domain-specific data augmentation enhances neural network training for medical imaging. A novel cut-paste strategy improved fetal ultrasound view classification, matching traditional methods.

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

470

Related Experiment Videos

Last Updated: Aug 6, 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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

470

Area of Science:

  • Medical Imaging
  • Machine Learning
  • Computer Vision

Background:

  • Domain-specific data augmentation is underutilized in medical imaging despite its potential.
  • Traditional data augmentation methods may not fully capture the nuances of medical image datasets.

Purpose of the Study:

  • To evaluate the efficacy of domain-specific data augmentation for medical imaging tasks.
  • To assess a context-preserving cut-paste augmentation strategy on fetal ultrasound datasets.

Main Methods:

  • Utilized fetal ultrasound datasets (FETAL-125, OB-125) for view classification.
  • Implemented a context-preserving cut-paste data augmentation strategy in an online fashion.
  • Compared performance against traditional data augmentation techniques.

Main Results:

  • The context-preserving cut-paste augmentation strategy generated valid training data, comparable to traditional methods.
  • FETAL-125 dataset achieved F-scores of 85.33 ± 0.24 with bespoke augmentation versus 86.89 ± 0.60.
  • OB-125 dataset achieved F-scores of 74.60 ± 0.11 with bespoke augmentation versus 72.43 ± 0.62.

Conclusions:

  • Domain-specific data augmentation, particularly the context-preserving cut-paste method, is effective for medical imaging tasks.
  • Online augmentation and class-balanced application are key considerations for bespoke augmentation design.
  • Open-source code is provided to enable wider adoption of these advanced augmentation techniques.