Search research articles

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

Sedimentary characteristics of Pu and <sup>237</sup>Np in the Pearl River Estuary under intensive land-ocean-human interactions.

Marine pollution bulletin·2025

Same author

Provenance and sedimentation of Pu and <sup>237</sup>Np in the northern Taiwan Strait suffering intensive land-ocean interaction.

Environmental pollution (Barking, Essex : 1987)·2024

Same author

Rapid Method To Determine <sup>137</sup>Cs, <sup>237</sup>Np, and Pu Isotopes in Seawater by SF-ICP-MS.

Analytical chemistry·2023

Same author

EG-TransUNet: a transformer-based U-Net with enhanced and guided models for biomedical image segmentation.

BMC bioinformatics·2023

Same author

Spatial variation, sources, and potential ecological risk of metals in sediment in the northern South China Sea.

Marine pollution bulletin·2022

Same author

A deep learning network based on multi-scale and attention for the diagnosis of chronic atrophic gastritis.

Zeitschrift fur Gastroenterologie·2022

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

Search research articles

Related Experiment Video

Updated: Jul 23, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

P-TransUNet: an improved parallel network for medical image segmentation.

Yanwen Chong¹, Ningdi Xie¹, Xin Liu¹

¹The State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China.

BMC Bioinformatics

|July 18, 2023

Summary

P-TransUNet enhances medical image segmentation by combining transformers and CNNs, focusing on local features and edge details. This novel approach improves accuracy, especially for lesion areas, outperforming existing methods.

Keywords:

Axis attention Channel attention Medical image segmentation Self-attention Transformer

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: Jul 23, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Medical Image Analysis
Deep Learning
Computer Vision

Background:

Convolutional Neural Networks (CNNs) struggle with long-range dependencies in medical image segmentation.
Transformer-based networks improve global context but often lack local feature extraction and require extensive data.
Existing methods overlook crucial edge information essential for precise segmentation.

Purpose of the Study:

To introduce P-TransUNet, a novel network designed to overcome limitations in current deep learning-based medical image segmentation.
To enhance the extraction of both local and long-range features while emphasizing critical edge information.
To improve segmentation accuracy and reduce data dependency compared to existing transformer-based models.

Main Methods:

Developed an efficient P-Transformer to capture distance-related long-range dependencies.
Integrated a fusion module to effectively combine long-range and local feature extraction.
Introduced an edge loss function to specifically guide the network towards accurate lesion boundary segmentation.

Main Results:

P-TransUNet demonstrated superior performance across four diverse medical image segmentation tasks.
The network successfully balanced the extraction of local and global contextual information.
Experimental results confirmed P-TransUNet's effectiveness in segmenting lesion areas with high precision.

Conclusions:

P-TransUNet offers a significant advancement in medical image segmentation by effectively integrating local and global feature extraction.
The incorporation of edge-aware learning and efficient transformer components leads to improved segmentation accuracy.
This novel architecture presents a promising solution for accurate and robust medical image segmentation, even with limited training data.