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

Geroprotective interventions preserve trabecular bone during ageing in female mice.

bioRxiv : the preprint server for biology·2026
Same author

Strong correlation between phantomless and inline phantom-based densitometric calibration of vertebral properties from CT scans of healthy volunteers.

Frontiers in bioengineering and biotechnology·2026
Same author

A generalisation study in deep learning-based segmentation of lower-limb muscles across different populations.

Scientific reports·2026
Same author

Prediction of compressive strength of vertebral body with metastatic lesions based on quantitative computed tomography-based subject-specific finite element models.

Bone·2026
Same author

Multi-scale modelling of mouse tibia loading reveals the critical role of muscle insertion surfaces.

Biomechanics and modeling in mechanobiology·2026
Same author

Aging reduces strain magnitude and heterogeneity while increasing apparent stiffness of the rat proximal tibia.

Journal of the mechanical behavior of biomedical materials·2026
Same journal

Analysis of strength degradation of coal and rock masses and stability of mined areas under long term immersion environment.

PloS one·2026
Same journal

Biogenic Silver-Selenium nanocomposite with anticancer activity and potent efficacy against vancomycin-resistant Staphylococcus aureus.

PloS one·2026
Same journal

Preparation and physicochemical characterization of a biodegradable chitosan/carboxymethyl cellulose hydrogel synthesized in NaOH/urea medium.

PloS one·2026
Same journal

Action-guilt, survivor-guilt, and depression in combat-related PTSD.

PloS one·2026
Same journal

Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability.

PloS one·2026
Same journal

Deep learning based two-way feature depiction model for brain tumor detection.

PloS one·2026
See all related articles

Related Experiment Video

Updated: Jun 11, 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

2.7K

A novel mean shape based post-processing method for enhancing deep learning lower-limb muscle segmentation accuracy.

Zhicheng Lin1, Enrico Dall'Ara2,3, Lingzhong Guo1,3

  • 1Department of Automatic Control and Systems Engineering, University of Sheffield, Sheffield, United Kingdom.

Plos One
|October 4, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a novel mean shape post-processing method to enhance lower-limb muscle segmentation accuracy from MRI scans. The approach improves diagnostic capabilities for musculoskeletal diseases by refining deep learning outputs.

More Related Videos

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.5K
Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

3.9K

Related Experiment Videos

Last Updated: Jun 11, 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

2.7K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.5K
Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

3.9K

Area of Science:

  • Medical Imaging and Image Analysis
  • Biomedical Engineering
  • Musculoskeletal Imaging

Background:

  • Accurate lower-limb muscle segmentation from Magnetic Resonance Imaging (MRI) is vital for diagnosing and treating musculoskeletal diseases.
  • Deep learning models like U-Net achieve good segmentation but can be further improved by post-processing techniques.
  • Existing post-processing methods often focus on general connectivity constraints, potentially overlooking anatomical specifics.

Purpose of the Study:

  • To develop and evaluate a novel post-processing method for improving lower-limb muscle segmentation accuracy using deep learning and MRI.
  • To leverage anatomical shape information through Statistical Shape Modelling (SSM) for enhanced segmentation refinement.
  • To compare the proposed mean shape (MS) based method against existing techniques and a commercial tool.

Main Methods:

  • A novel mean shape (MS) based post-processing technique was developed, integrating Statistical Shape Modelling (SSM).
  • The MS method was applied to fine-tune segmentation masks generated by deep learning models.
  • Performance was evaluated on MRI scans from two cohorts of post-menopausal women using metrics like Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and Average Symmetric Surface Distance (ASSD).

Main Results:

  • The MS-based method achieved a mean DSC of 0.83 across analyzed lower-limb muscles.
  • It demonstrated superior performance in terms of Hausdorff Distance (HD) at 20.6 mm and Average Symmetric Surface Distance (ASSD) at 2.1 mm.
  • The method outperformed existing post-processing techniques and a commercial semi-automatic segmentation tool.

Conclusions:

  • Incorporating anatomical mean shape information via SSM significantly enhances the accuracy of lower-limb muscle segmentation from MRI.
  • The proposed MS-based post-processing method is effective and shows potential for broader applications in biological organ segmentation.
  • This approach offers a promising avenue for improving diagnostic and therapeutic processes in musculoskeletal imaging.