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

Visceral adiposity and breast cancer outcomes: transcriptomic analysis of the tumor microenvironment by intrinsic subtype.

Breast cancer research : BCR·2026
Same author

Validation and application of automated CT analysis to musculoskeletal profiling in MVC occupants.

Traffic injury prevention·2026
Same author

Real-world incidence of cancer therapy-related cardiac dysfunction in a large, diverse, and contemporary cohort.

ESC heart failure·2026
Same author

AI-Driven Bone and Marrow Segmentation on FLT-PET/CT: Technical Multi-organ Validation in AML and HCT.

Research square·2026
Same author

DXA-Derived Abdominal Adiposity and Obesity-Related Cancer Risk Among Postmenopausal Women in the Women's Health Initiative.

Obesity (Silver Spring, Md.)·2026
Same author

Longitudinal analysis of body compositions following Roux-en-Y gastric bypass.

Langenbeck's archives of surgery·2026

Related Experiment Video

Updated: Dec 10, 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

3.2K

Deep learning method for localization and segmentation of abdominal CT.

Setareh Dabiri1, Karteek Popuri1, Cydney Ma1

  • 1School of Engineering Science, Simon Fraser University, Canada.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|August 31, 2020
PubMed
Summary

This study introduces an automated method to analyze body composition from CT scans by accurately identifying the L3 vertebra slice and segmenting muscle and fat tissues. This AI-driven approach enhances efficiency and accuracy in body composition analysis.

Keywords:
CT scanConvolutional neural networkFat segmentationMuscle segmentationThird lumbar vertebra

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

678
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

43.2K

Related Experiment Videos

Last Updated: Dec 10, 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

3.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

678
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

43.2K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Computed Tomography (CT) imaging is crucial for body composition analysis, assessing muscle and fat proportions.
  • Manual selection of the L3 vertebral slice and segmentation of tissues is time-consuming and labor-intensive.
  • Accurate body composition analysis has applications in nutrition, oncology, and chemotherapy dose design.

Purpose of the Study:

  • To develop an automated algorithm for L3 axial slice localization in CT scans.
  • To segment key body composition tissues: skeletal muscle (SM), subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and intermuscular adipose tissue (IMAT).
  • To enable fully automated and accurate body composition analysis from CT volumes.

Main Methods:

  • A two-stage deep learning approach: an L3 localization network followed by a muscle-fat segmentation network.
  • The localization network is a fully convolutional classifier trained on over 12,000 images.
  • The segmentation network utilizes a convolutional neural network with an encoder-decoder architecture, trained on diverse cancer patient CT datasets.

Main Results:

  • Achieved a mean L3 slice localization error of 0.87±2.54 on 1748 CT scan volumes.
  • Demonstrated high segmentation accuracy with mean Jaccard scores of 97% for SM and VAT.
  • Attained mean Jaccard scores of 98% for SAT and 83% for IMAT on test datasets.

Conclusions:

  • The developed automated localization and segmentation networks show significant potential for high-accuracy body composition analysis.
  • This AI-driven method can streamline workflows in clinical and research settings.
  • The findings support the feasibility of fully automated body composition assessment using CT imaging.