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

Multi-representational deep transfer learning for classifying hemorrhagic metastases and non-neoplastic intracranial hematomas in multi-modal brain MRI scans.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025
Same author

TNCB: Tri-Net With Cross-Balanced Pseudo Supervision for Class Imbalanced Medical Image Classification.

IEEE journal of biomedical and health informatics·2024
Same author

A Siamese-Transport Domain Adaptation Framework for 3D MRI Classification of Gliomas and Alzheimer's Diseases.

IEEE journal of biomedical and health informatics·2023
Same author

SDPN: A Slight Dual-Path Network With Local-Global Attention Guided for Medical Image Segmentation.

IEEE journal of biomedical and health informatics·2023
Same author

[Surgical treatment of 402 consecutive cases for hilar cholangiocarcinoma: Chinese single center experience].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2007
Same author

Highly convergent route to cyclopeptide alkaloids: total synthesis of ziziphine N.

Organic letters·2007

Related Experiment Video

Updated: Aug 2, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

470

TT-Net: Tensorized Transformer Network for 3D medical image segmentation.

Jing Wang1, Aixi Qu1, Qing Wang2

  • 1Shandong University, School of Information Science and Engineering, Qingdao 266237, China.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|April 19, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces the Tensorized Transformer Network (TT-Net) for improved medical image segmentation. TT-Net effectively addresses challenges in variable target shapes and high parametric complexity, outperforming existing methods.

Keywords:
Automatic segmentationExplainabilityMulti-scaleTensorized Transformer

More Related Videos

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

2.8K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Related Experiment Videos

Last Updated: Aug 2, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

470
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

2.8K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Area of Science:

  • Medical imaging analysis
  • Computer-assisted diagnosis
  • Artificial intelligence in healthcare

Background:

  • Accurate segmentation of organs, tissues, and lesions is crucial for computer-assisted diagnosis.
  • Existing automatic segmentation methods struggle with variations in target location, size, shape, and imaging modalities.
  • Current transformer-based networks exhibit high parametric complexity, limiting their practical application.

Purpose of the Study:

  • To propose a novel Tensorized Transformer Network (TT-Net) to overcome limitations in current medical image segmentation techniques.
  • To enhance the capture of context interaction information and global multi-variate dependencies.
  • To reduce parametric complexity in transformer-based segmentation models.

Main Methods:

  • Developed a Multi-scale transformer with layers-fusion to capture context interaction information.
  • Introduced a Cross Shared Attention (CSA) module utilizing pHash similarity fusion (pSF) for global multi-variate dependency feature extraction.
  • Proposed a Tensorized Self-Attention (TSA) module to manage high parametric complexity and enable easy integration into other models.

Main Results:

  • TT-Net demonstrated superior performance across four different segmentation tasks on public and clinical datasets with diverse imaging modalities.
  • The proposed method achieved state-of-the-art results, outperforming existing segmentation approaches.
  • An embedded compression module offered reduced computation with comparable segmentation performance, applicable to other transformer-based methods.

Conclusions:

  • TT-Net effectively addresses limitations in medical image segmentation, offering improved accuracy and efficiency.
  • The network's design, including CSA and TSA modules, enhances feature extraction and parameter management.
  • TT-Net provides a promising solution for computer-assisted diagnosis, with potential for broader application in medical imaging analysis.