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

Pediatric infection imaging focusing on FDG PET/CT: Techniques, safety, and indications.

Seminars in nuclear medicine·2026
Same author

Dual energy CT of pediatric genitourinary disorders.

Abdominal radiology (New York)·2025
Same author

ACR-ACNM-ARS-SNMMI-SPR Practice Parameter for Treatment of Benign and Malignant Thyroid Disease With I-131 Sodium Iodide.

American journal of clinical oncology·2025
Same author

Cancer Detection in Breast MRI Screening via Explainable AI Anomaly Detection.

Radiology·2025
Same author

Artifacts and pitfalls in pediatric head computed tomography: physics, principles, and clinical impact.

Pediatric radiology·2025
Same author

Nuclear Cerebrospinal Fluid Imaging: Guide to Procedures and Interpretation.

Radiographics : a review publication of the Radiological Society of North America, Inc·2025
Same journal

The invisible footprint: why planetary health is a pediatric radiologist's obligation.

Pediatric radiology·2026
Same journal

The radiographic bubbly fecal pattern of intestinal pneumatosis in newborns revisited.

Pediatric radiology·2026
Same journal

Regional differences in fetal fat accretion in small-for-gestational-age fetuses assessed by quantitative magnetic resonance imaging.

Pediatric radiology·2026
Same journal

Thermal ablation of lung metastases in children: what every paediatric radiologist should know.

Pediatric radiology·2026
Same journal

Prediction of early recurrence in primary intussusception: development of an ultrasound-based radiomics and deep learning nomogram.

Pediatric radiology·2026
Same journal

Pediatric SARS-CoV-2 long term outcomes study: chest radiographic and computed tomography findings at baseline.

Pediatric radiology·2026
See all related articles

Related Experiment Video

Updated: Dec 30, 2025

A Coregistered Ultrasound and Photoacoustic Imaging Protocol for the Transvaginal Imaging of Ovarian Lesions
10:21

A Coregistered Ultrasound and Photoacoustic Imaging Protocol for the Transvaginal Imaging of Ovarian Lesions

Published on: March 3, 2023

2.1K

Ovarian torsion: developing a machine-learned algorithm for diagnosis.

Jeffrey P Otjen1, A Luana Stanescu2, Adam M Alessio3

  • 1Department of Radiology, Seattle Children's Hospital and the University of Washington, Seattle Children's Hospital, MA.7.220, 4800 Sand Point Way NE, Seattle, WA, 98105, USA. jeffrey.otjen@seattlechildrens.org.

Pediatric Radiology
|January 24, 2020
PubMed
Summary
This summary is machine-generated.

This study developed a machine learning algorithm to improve the diagnosis of ovarian torsion in children. The algorithm uses ultrasound features to accurately detect ovarian torsion, aiding timely treatment and preserving fertility.

Keywords:
AlgorithmChildrenMachine learningMedializationOvaryTorsionUltrasound

More Related Videos

Author Spotlight: Advanced Ex Vivo Model for Investigating Cancer-Adipose Microenvironment Interaction
05:42

Author Spotlight: Advanced Ex Vivo Model for Investigating Cancer-Adipose Microenvironment Interaction

Published on: January 26, 2024

3.1K
Tubal Cytology of the Fallopian Tube as a Promising Tool for Ovarian Cancer Early Detection
08:09

Tubal Cytology of the Fallopian Tube as a Promising Tool for Ovarian Cancer Early Detection

Published on: July 25, 2017

12.8K

Related Experiment Videos

Last Updated: Dec 30, 2025

A Coregistered Ultrasound and Photoacoustic Imaging Protocol for the Transvaginal Imaging of Ovarian Lesions
10:21

A Coregistered Ultrasound and Photoacoustic Imaging Protocol for the Transvaginal Imaging of Ovarian Lesions

Published on: March 3, 2023

2.1K
Author Spotlight: Advanced Ex Vivo Model for Investigating Cancer-Adipose Microenvironment Interaction
05:42

Author Spotlight: Advanced Ex Vivo Model for Investigating Cancer-Adipose Microenvironment Interaction

Published on: January 26, 2024

3.1K
Tubal Cytology of the Fallopian Tube as a Promising Tool for Ovarian Cancer Early Detection
08:09

Tubal Cytology of the Fallopian Tube as a Promising Tool for Ovarian Cancer Early Detection

Published on: July 25, 2017

12.8K

Area of Science:

  • Pediatric Radiology
  • Medical Imaging Analysis
  • Machine Learning in Healthcare

Background:

  • Ovarian torsion is a critical pediatric emergency causing pelvic pain, with diagnosis challenging via physical exam, history, and imaging.
  • Delayed diagnosis of ovarian torsion can lead to irreversible ovarian damage and impact future fertility.
  • Ultrasound is the primary imaging modality for pediatric ovarian torsion, but its features are not always definitive.

Purpose of the Study:

  • To develop a machine learning algorithm for diagnosing ovarian torsion in pediatric patients using sonographic features.
  • To evaluate the diagnostic performance of individual sonographic elements and combined algorithmic approaches.

Main Methods:

  • Retrospective analysis of 119 surgically confirmed pediatric ovarian torsion cases and 331 controls over 11 years.
  • Data collected included ovarian volumes, position, Doppler flow, follicles, masses, and free fluid.
  • Machine learning algorithms, including decision trees, were trained and validated on sonographic features.

Main Results:

  • A decision tree algorithm combining ovarian flow, follicles, volume, and masses achieved an AUC of 0.96±0.07.
  • Individual features showed modest performance (AUCs 0.66-0.82), while the combined algorithm demonstrated high diagnostic accuracy.
  • The algorithm achieved a sensitivity of 95±14% and specificity of 92±2%.

Conclusions:

  • Machine learning-based algorithms can significantly enhance the accuracy of diagnosing pediatric ovarian torsion compared to single-feature analysis.
  • A clinically pragmatic decision tree algorithm offers high sensitivity and specificity for detecting ovarian torsion.
  • This approach aids radiologists in timely diagnosis, potentially preventing ovarian ischemia and preserving fertility.