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 Experiment Video

Updated: May 27, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

CTransFuse: A Hybrid Transformer-CNN Framework for Precise Meniscus Segmentation and Lesion Identification.

Yane Li, Qinuo Zhang, Wenjing Wang

    IEEE Journal of Biomedical and Health Informatics
    |May 25, 2026
    PubMed
    Summary

    A new AI model, CTransFuse, accurately identifies knee meniscus tears and degenerative changes using MRI. This efficient framework improves lesion detection and classification for better clinical assessment.

    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

    Discharge planning services for safe transition after hip fracture: a systematic review and meta-analysis of discharge readiness, functional recovery, and complication reduction.

    PeerJ·2026
    Same author

    Modelling the risk of West Nile virus infection in seven European countries from published serological and case notification data, 2008 to 2022.

    Euro surveillance : bulletin Europeen sur les maladies transmissibles = European communicable disease bulletin·2026
    Same author

    GraphLooper: predicting chromatin loops based on hierarchical multi-view graph pooling method.

    Briefings in bioinformatics·2026
    Same author

    A bioengineered extracellular vesicle-based platform for targeted codelivery and multi-mechanistic therapy of skin fibrosis.

    International journal of pharmaceutics·2026
    Same author

    Ex Vivo Human Foreskin Tissue Circumcision via High-Frequency Electric Welding.

    Bioengineering (Basel, Switzerland)·2026
    Same author

    A novel antisense lncRNA, LPCRL, functions as a molecular scaffold for the USP15/MIB1 complex to promote primary cisplatin resistance and tumor progression in lung squamous cell carcinoma.

    Journal of experimental & clinical cancer research : CR·2026

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Computer Vision

    Background:

    • Meniscal tears and degenerative changes are common knee pathologies.
    • Automated analysis of knee MRI is challenging due to lesion characteristics like indistinct boundaries and heterogeneous intensity.

    Purpose of the Study:

    • To propose CTransFuse, a hybrid CNN-Transformer framework for lesion-aware meniscus segmentation and identification in knee MRI.
    • To improve the accuracy and efficiency of automated knee MRI analysis.

    Main Methods:

    • CTransFuse utilizes a parallel dual-branch design combining CNNs and Transformers.
    • A lightweight multi-scale pyramid Transformer encoder (CosFormer) extracts global representations.
    • A bidirectional attention fusion module (BiFusion) enhances cross-level feature interaction.

    Related Experiment Videos

    Last Updated: May 27, 2026

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    Main Results:

    • CTransFuse achieves high inference speed (177.6 fps) with low parameters (12.6M).
    • Segmentation performance includes Dice scores of 79.28% (tears) and 82.57% (degeneration), and mIoU of 83.25% (tears) and 87.18% (degeneration).
    • Classification performance shows AUC of 97.45% and AUPR of 97.49%, demonstrating robustness in imbalanced conditions.

    Conclusions:

    • CTransFuse offers an efficient and accurate solution for knee MRI analysis.
    • The framework shows strong generalization capabilities on public datasets.
    • CTransFuse has potential for intelligent knee MRI analysis and computer-aided clinical assessment.