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

Dipolar Order Mapping Based on Spin-Lock Magnetic Resonance Imaging.

NMR in biomedicine·2026

Same author

Latent profiles of environmental awareness in Chinese college students: effects of psychological capital and digital engagement.

Frontiers in psychology·2026

Same author

A dual mode turn-on probe for H<sub>2</sub>O<sub>2</sub> sensing <i>via</i> fluorescence and colorimetry in live cells and serum.

Analytical methods : advancing methods and applications·2026

Same author

Diagnostic Performance of Quantitative T1rho MRI for the Assessment of Disease Activity in Relapsing-Remitting Multiple Sclerosis.

Academic radiology·2026

Same author

A knowledge-based deep learning model for accurate urban drainage system prediction under spatiotemporally variable rainfall.

Water research·2026

Same author

Associations of psychological capital latent profiles with depression and anxiety: A cross-sectional study in Chinese college students.

Public health·2026

Same journal

SynTME: A tumor microenvironment-aware, pharmacology-inspired multi-stage framework for drug synergy prediction.

Computer methods and programs in biomedicine·2026

Same journal

MMFVS-Net: A triple-symmetric cross-attention network for multimodal optical image fusion and high-accuracy virtual staining of breast cancer tissues.

Computer methods and programs in biomedicine·2026

Same journal

A novel Milstein-stochastic epidemiologically-informed neural network for approaching epidemic dynamics: Application to Mpox disease.

Computer methods and programs in biomedicine·2026

Same journal

Accounting for approximation errors using surrogate-based parameter estimation of cardiac mechanics digital twins.

Computer methods and programs in biomedicine·2026

Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026

Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 6, 2025

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

Deep collaborative network with alpha matte for precise knee tissue segmentation from MRI.

Sheheryar Khan¹, Basim Azam², Yongcheng Yao³

¹Department of Imaging and Interventional Radiology, CU lab of AI in radiology (CLAIR), Chinese University of Hong Kong, Prince of Wales Hospital, Shatin N.T., Hong Kong, China; School of Professional Education and Executive Development, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China.

Computer Methods and Programs in Biomedicine

|June 25, 2022

Summary

This summary is machine-generated.

This study introduces a deep learning framework for precise knee tissue segmentation in MRI, achieving high accuracy for cartilage and other tissues. The method improves segmentation by using low-rank tensor reconstruction and trimap generation for better boundary definition.

Keywords:

Alpha matting Cartilage and meniscus segmentation Convolutional neural network Knee MRI Low rank decomposition Trimap

More Related Videos

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Related Experiment Videos

Last Updated: Sep 6, 2025

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

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Area of Science:

Medical Imaging
Artificial Intelligence
Biomedical Engineering

Background:

Precise segmentation of knee tissues in MRI is essential for quantitative imaging and diagnosis.
Current deep learning methods (CNNs) struggle with low contrast and inhomogeneities, leading to incomplete segmentation.

Purpose of the Study:

To develop an automatic deep learning framework for accurate knee tissue segmentation.
To address limitations of existing methods in handling image-specific adaptations and boundary regions.

Main Methods:

A novel deep collaborative method combining an encoder-decoder network with low-rank tensor reconstruction.
Utilizing trimap generation to define confidence regions and improve boundary segmentation.
Solving segmentation as an alpha matting problem for precise blending.

Main Results:

Achieved an overall segmentation Dice score of 0.8925 on Osteoarthritis Initiative (OAI) datasets for all 6 musculoskeletal tissues.
Femoral and Tibial cartilage segmentation exceeded an average Dice score of 0.9.
Volumetric metrics confirmed superior performance across all tissue compartments.

Conclusions:

The proposed method effectively segments knee tissues, validated on OAI and custom datasets.
Incorporating an extra prediction scale enhanced the model's ability to accurately segment tissue boundaries.
Demonstrated application in cartilage segmentation for creating diagnostic thickness maps.