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 Experiment Video

Updated: Sep 17, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K

Establishment and Reliability of an Automatic Measurement Method of Pectus Excavatum Indices Using a Deep Learning

Xicheng Deng1, Siping He2, Jiayi Lin1

  • 1Department of Cardiothoracic Surgery, The Affiliated Children's Hospital of Xiangya School of Medicine, Central South University, Hunan Children's Hospital, Changsha, CHN.

Cureus
|June 30, 2025
PubMed
Summary

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

PCSK5 promotes angiogenesis and cardiac repair after myocardial infarction.

Nature communications·2026
Same author

A novel borondifluoro indolenine-functionalized red-shift ratiometric fluorescent probe for detection of hypochlorous acid in drug-induced liver injury.

Talanta·2026
Same author

Food-Grade Microemulsion for High-Loading Octacosanol: Formulation Optimization, Characterization, and Biological Evaluation.

Foods (Basel, Switzerland)·2026
Same author

Exploring healthcare professionals' views on integrative Chinese-Western medicine in the nutritional management of cancer patients: a qualitative study.

Frontiers in nutrition·2026
Same author

U.S. Veteran Interest in Peer Specialists' Help to Enhance Suicide Safety Plans: Understanding Veteran Perspectives on Safety Plan Engagement.

Journal of military social work and behavioral health services·2026
Same author

Exploratory transcriptomic analysis suggests candidate genes associated with loss of response to ustekinumab in Crohn's disease.

Frontiers in genetics·2026

Automated U-Net segmentation reliably measures pectus excavatum (PE) severity indices, reducing observer variability. This AI approach enhances clinical workflow efficiency for PE evaluation.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Thoracic Surgery

Background:

  • Pectus excavatum (PE) assessment relies on subjective manual measurements, leading to interobserver variability.
  • Standardizing PE severity evaluation is crucial for consistent clinical management and treatment planning.

Purpose of the Study:

  • To evaluate the consistency and accuracy of U-Net-based automated segmentation for PE indices.
  • To compare automated measurements against manual assessments and assess interobserver variability reduction.

Main Methods:

  • Developed a U-Net model trained on 550 chest CT scans, validated on 164 independent scans.
  • Calculated Haller, correction, and asymmetry indices automatically and compared with four manual observers.
  • Analyzed measurement accuracy, interobserver variability, and agreement using statistical methods (ICC, Bland-Altman).
Keywords:
asymmetry indexcorrection indexdeep learninghaller indexpectus excavatumu-net

More Related Videos

Precision Measurements and Parametric Models of Vertebral Endplates
10:35

Precision Measurements and Parametric Models of Vertebral Endplates

Published on: September 17, 2019

6.6K

Related Experiment Videos

Last Updated: Sep 17, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K
Precision Measurements and Parametric Models of Vertebral Endplates
10:35

Precision Measurements and Parametric Models of Vertebral Endplates

Published on: September 17, 2019

6.6K

Main Results:

  • Manual measurements had an initial error rate of 15.9%, reduced to 4.1% post-consensus (p<0.01).
  • U-Net model showed stable error rates (8.7% vs 8.5%, p=0.91).
  • Strong agreement between automated and corrected manual measurements: Haller (ICC=0.83), correction (ICC=0.86), asymmetry (ICC=0.92).

Conclusions:

  • U-Net-based automation offers reliable PE severity index measurement.
  • Automated segmentation can significantly reduce observer-dependent variability in PE assessment.
  • Further multi-center validation is recommended for broader clinical adoption in radiology.