Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

CDK2 Inhibition Exerts RB-Independent Antitumor Activity in CDK4/6 Inhibitor-Resistant HR+/HER2- Breast Cancer.

Cancer research·2026

Same author

Longitudinal Language-Model Reasoning Enables Automated Labeling of Lung Cancer Recurrence from Unstructured Clinical Records.

Research square·2026

Same author

OMAMA-DB: the Oregon-Massachusetts Mammography Database.

Journal of medical imaging (Bellingham, Wash.)·2026

Same author

Lung cancer screening in transition: highlights from the 3rd Oslo Lung Cancer Symposium, 2025.

European clinical respiratory journal·2026

Same author

Effect of Age and Sex on Normalized Automated DECT-Derived Pulmonary Iodine Concentration.

Diagnostics (Basel, Switzerland)·2026

Same author

Detecting and Mitigating Bias for Inclusive and Trustworthy Clinical Research: A Scientific Statement From the American Heart Association.

Circulation. Genomic and precision medicine·2026

Same journal

Bayesian Convolutional Neural Networks in Medical Imaging Classification: A Promising Solution for Deep Learning Limits in Data Scarcity Scenarios.

Journal of digital imaging·2023

Same journal

Detecting and Characterizing Inferior Vena Cava Filters on Abdominal Computed Tomography with Data-Driven Computational Frameworks.

Journal of digital imaging·2023

Same journal

DMCA-GAN: Dual Multilevel Constrained Attention GAN for MRI-Based Hippocampus Segmentation.

Journal of digital imaging·2023

Same journal

Left Ventricular Myocardial Dysfunction Evaluation in Thalassemia Patients Using Echocardiographic Radiomic Features and Machine Learning Algorithms.

Journal of digital imaging·2023

Same journal

Public Imaging Datasets of Gastrointestinal Endoscopy for Artificial Intelligence: a Review.

Journal of digital imaging·2023

Same journal

External Validation of Robust Radiomic Signature to Predict 2-Year Overall Survival in Non-Small-Cell Lung Cancer.

Journal of digital imaging·2023

See all related articles

Search research articles

Related Experiment Video

Updated: Feb 27, 2026

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography

Published on: November 8, 2024

Pixel-Level Deep Segmentation: Artificial Intelligence Quantifies Muscle on Computed Tomography for Body Morphometric

Hyunkwang Lee¹, Fabian M Troschel¹, Shahein Tajmir¹

¹Department of Radiology, Massachusetts General Hospital, 25 New Chardon Street, Suite 400B, Boston, MA, 02114, USA.

Journal of Digital Imaging

|June 28, 2017

Summary

This summary is machine-generated.

A new deep learning system automates skeletal muscle segmentation from CT scans, improving pretreatment risk stratification for personalized medicine. This objective approach replaces subjective assessments, enhancing patient care and predicting surgical or chemotherapy tolerance.

Keywords:

Artificial intelligence Computed tomography Computer-aided diagnosis (CAD)Convolutional neural networks Deep learning Muscle segmentation

More Related Videos

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Published on: March 21, 2021

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

Published on: November 27, 2017

Related Experiment Videos

Last Updated: Feb 27, 2026

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography

Published on: November 8, 2024

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Published on: March 21, 2021

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

Published on: November 27, 2017

Area of Science:

Medical Imaging
Artificial Intelligence
Personalized Medicine

Background:

Pretreatment risk stratification is crucial for personalized medicine, but current methods like the "eyeball test" are subjective.
Morphometric age from imaging correlates with patient outcomes but is time-consuming and requires expert analysis.
Automated, quantitative methods are needed to improve the accuracy and efficiency of risk assessment.

Purpose of the Study:

To develop a fully automated deep learning system for skeletal muscle cross-sectional area (CSA) segmentation.
To assess the model's performance across varying imaging parameters (WL, WW, bit resolution).
To provide a tool for accelerating muscle quantification in clinical settings.

Main Methods:

A fully automated deep learning model based on a fully convolutional network was employed.
ImageNet pre-trained weights were used for initialization, followed by post-processing to remove intramuscular fat.
The model was trained on 250 CT images and tested on 150 held-out cases, with experiments varying imaging parameters.

Main Results:

The best model achieved a Dice similarity coefficient (DSC) of 0.93 ± 0.02.
The system demonstrated a mean difference of 3.68 ± 2.29% between predicted and ground truth muscle CSA.
Model performance was evaluated under different window level, window width, and bit resolution settings.

Conclusions:

The developed automated deep learning system accurately segments skeletal muscle CSA from CT images.
This system offers a rapid and objective alternative to subjective assessments for pretreatment risk stratification.
The technology has the potential to be integrated into clinical workflows for enhanced patient management and can be expanded for 3D volumetric analysis.