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

Development of a Rapid and Sensitive AlphaLISA-Based Assay for Lassa Virus Glycoprotein Detection.

Pathogens (Basel, Switzerland)·2026

Same author

Edge guided bidirectional iterative network in medical image segmentation.

Scientific reports·2025

Same author

Polysaccharide conjugate vaccines: From historical milestones to future strategies.

Carbohydrate polymers·2025

Same author

Trace Detection of Staphylococcal Enterotoxin B Based on Hydrogen-Terminated Diamond Solution-Gate Field-Effect Transistor.

Analytical chemistry·2025

Same author

FCP-Former: Enhancing Long-Term Multivariate Time Series Forecasting with Frequency Compensation.

Sensors (Basel, Switzerland)·2025

Same author

AI-Enhanced Electrochemical Sensing Systems: A Paradigm Shift for Intelligent Food Safety Monitoring.

Biosensors·2025

Search research articles

Related Experiment Video

Updated: Sep 10, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

A fully automatic knee subregion segmentation network based on tissue segmentation and anatomical geometry.

Shaolong Chen^1,2, Lijie Zhong³, Zhiyong Zhang⁴

¹School of Sino-German Intelligent Manufacturing, Shenzhen City Polytechnic, Shenzhen, 518000, China.

Scientific Reports

|August 19, 2025

Summary

This study introduces an automated knee MRI segmentation network for precise bone and cartilage subregion delineation. The method accurately identifies knee sides and divides tissues using anatomical geometry, improving segmentation accuracy.

More Related Videos

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Sep 10, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Area of Science:

Medical Imaging
Artificial Intelligence
Orthopedics

Background:

Knee MRI segmentation is challenging due to numerous subregions and indistinct boundaries.
Accurate subregion segmentation is crucial for diagnosing knee conditions and guiding treatment.

Purpose of the Study:

To develop a fully automatic network for knee MRI bone and cartilage subregion segmentation.
To improve the precision and efficiency of knee MRI analysis.

Main Methods:

A transformer-based network for multilevel region and edge aggregation was employed for precise tissue edge segmentation.
A fibula detection module was designed to determine knee laterality (medial/lateral).
A boundary-based subregion segmentation module was developed to divide bone and cartilage tissues.

Main Results:

The method achieved 1.000 accuracy in detecting medial and lateral knee sides using the fibula classification dataset.
Average Dice scores of 0.953 for bone subregions and 0.831 for cartilage subregions were obtained on the knee MRI dataset.
The developed datasets support model training and validation.

Conclusions:

The proposed network effectively segments knee MRI bone and cartilage subregions.
The integration of tissue segmentation and anatomical geometry enhances segmentation accuracy.
This automated approach offers a reliable solution for complex knee MRI analysis.