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

Classification of Skeletal Muscle Fibers

Classification of Skeletal Muscle Fibers

Skeletal muscles continuously produce ATP to provide the energy that enables muscle contractions. Skeletal muscle fibers can be categorized into three types based on differences in their contraction speed and how they produce ATP, as well as physical differences related to these factors. Most human muscles contain all three muscle fiber types, albeit in varying proportions.
Slow-Twitch Muscle Fibers
Slow oxidative, muscle fibers appear red due to large numbers of capillaries and high levels of...

You might also read

Related Articles

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

Sort by

Same author

Integrated Downstream Analysis and Epidemiological Modelling of Hantavirus Infection: From Host Transcriptomics to Transmission Dynamics.

Pathogens (Basel, Switzerland)·2026

Same author

Tezepelumab in severe asthma: chest computed tomography assessment of airway remodeling and clinical remission.

Frontiers in pharmacology·2026

Same author

Quantification and Analysis of Lung Involvement by Artificial Intelligence in Patients with Progressive Pulmonary Fibrosis Treated with Nintedanib.

Medicina (Kaunas, Lithuania)·2025

Same author

Differential causal networks highlight sex-based differences in human tissues.

Briefings in bioinformatics·2025

Same author

Combined Model for the Diagnosis of Hepatocellular Carcinoma: A Pilot Study Comparing the Liver to Spleen Volume Ratio and Liver Vein to Cava Attenuation.

Journal of clinical medicine·2025

Same author

Pituitary enlargement and hypopituitarism in patient with lung cancer treated with immune checkpoint inhibitors: Metastasis or hypophysitis? Role of imaging.

Radiology case reports·2025

Search research articles

Related Experiment Video

Updated: Sep 10, 2025

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

Deep Learning-Based 3D and 2D Approaches for Skeletal Muscle Segmentation on Low-Dose CT Images.

Giuseppe Timpano¹, Pierangelo Veltri², Patrizia Vizza³

¹Department of Surgical and Medical Sciences, Magna Graecia University, Catanzaro, 88100, Italy. giuseppe.timpano@unicz.it.

Journal of Imaging Informatics in Medicine

|August 27, 2025

Summary

This summary is machine-generated.

Deep learning models automate skeletal muscle segmentation in low-dose CT scans. The 2D DeepLabv3+ model achieved superior accuracy, while the 3D UNet3+ model offered efficiency for body composition analysis.

Keywords:

Deep learning DeepLab LDCT Segmentation Skeletal muscle UNet

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Related Experiment Videos

Last Updated: Sep 10, 2025

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

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Area of Science:

Medical Imaging
Artificial Intelligence
Radiology

Background:

Automated skeletal muscle segmentation from CT images is crucial for quantitative body composition analysis.
Manual segmentation is labor-intensive and not feasible for high-throughput studies.
Standardization at the third lumbar vertebra (L3) level is key for muscle quantification.

Purpose of the Study:

To systematically compare 2D and 3D deep learning architectures for skeletal muscle segmentation in LDCT scans.
To evaluate DeepLabv3+ (2D) and UNet3+ (3D) performance at the L3 vertebral level.
To provide insights for selecting optimal architectures in automated muscle segmentation workflows.

Main Methods:

Implementation and evaluation of DeepLabv3+ (2D) and UNet3+ (3D) architectures.
Utilized a dataset of 537 low-dose CT (LDCT) scans with preprocessing and L3 slice selection.
Assessed performance using Dice Similarity Coefficient (DSC) and 95th percentile Hausdorff Distance (HD95).

Main Results:

DeepLabv3+ (2D) demonstrated superior segmentation accuracy (DSC = 0.982 ± 0.010).
UNet3+ (3D) showed competitive results (DSC = 0.967 ± 0.013) with significantly fewer parameters and faster inference.
Both models met or surpassed existing literature benchmarks for CT-based muscle segmentation.

Conclusions:

Deep learning models effectively automate skeletal muscle segmentation in LDCT scans.
DeepLabv3+ offers high accuracy, while UNet3+ provides an efficient alternative for L3 muscle quantification.
This study guides the selection of deep learning architectures for robust body composition analysis.