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: Jan 12, 2026

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

3.3K

M-AECA Net: A Mamba-Based Auxiliary Encoder With Cross-Attention Fusion Network for PET/CT Tumor Segmentation.

Hengzhi Xue, Yudong Yao, Yueyang Teng

    IEEE Journal of Biomedical and Health Informatics
    |November 5, 2025
    PubMed
    Summary
    This summary is machine-generated.

    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

    High-speed quantitative X-ray multi-contrast imaging with deep learning based modulated pattern analysis.

    Journal of synchrotron radiation·2026
    Same author

    Generative Models for Medical Image Creation and Translation: A Scoping Review.

    Sensors (Basel, Switzerland)·2026
    Same author

    A method for heart sound classification using sample augmentation and INDANet.

    The Review of scientific instruments·2026
    Same author

    Automated Prediction of Subsequent Miscarriage Risk in Pregnant Women by Early First-trimester Ultrasound Characteristics Based on the Convolutional Neural Network Model.

    IEEE journal of biomedical and health informatics·2026
    Same author

    Deep Learning-Driven Innovations in Echocardiography: Taxonomy, Clinical Impact, Challenges, and Opportunities.

    Annals of biomedical engineering·2025
    Same author

    Under-Urine-Adhered Supramolecular Hydrogel with Linearly Sustained Quercetin Release Facilitates Hemorrhagic Cystitis Healing via Inflammation Regulation.

    Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025

    This study introduces M-AECA, an AI model enhancing medical image segmentation for radiotherapy. It improves tumor delineation accuracy, crucial for precise cancer treatment planning.

    Area of Science:

    • Medical Imaging Analysis
    • Artificial Intelligence in Oncology
    • Radiotherapy Planning

    Background:

    • Positron emission tomography (PET) and computed tomography (CT) fusion provides vital metabolic and anatomical tumor data for diagnosis, staging, and treatment evaluation.
    • Accurate tumor segmentation is critical for radiotherapy, but challenging due to fuzzy boundaries, uncertain locations, and multifocal disease.
    • Existing segmentation methods struggle with the complexities of diverse tumor characteristics.

    Purpose of the Study:

    • To develop an advanced AI model for accurate and automatic tumor segmentation in PET/CT images.
    • To improve the precision of target delineation for radiotherapy planning.
    • To enhance feature extraction and fusion for robust tumor segmentation.

    Main Methods:

    More Related Videos

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    731

    Related Experiment Videos

    Last Updated: Jan 12, 2026

    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

    3.3K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    731
    • Extended the STUNet model, pre-trained on the TotalSegmentator dataset.
    • Integrated a Mamba-based auxiliary encoder (M-AE) for multi-scale global feature extraction.
    • Developed an Inter-Branch Feature Fusion Module (IBFFM) utilizing cross-attention and feature subspace projection for comprehensive feature fusion.

    Main Results:

    • The proposed M-AECA model achieved superior performance on the Hecktor and AutoPET datasets compared to existing methods.
    • Average Dice similarity coefficients of 70.86% (Hecktor) and 64.91% (AutoPET) were obtained in the test sets.
    • Ablation experiments confirmed the significant contributions of the M-AE and IBFFM components.

    Conclusions:

    • The M-AECA model offers a significant advancement in automatic tumor segmentation for radiotherapy.
    • The integration of Mamba-based encoding and advanced feature fusion enhances segmentation accuracy.
    • This approach holds promise for improving radiotherapy planning and patient outcomes.