TransBridge: a lightweight transformer for left ventricle segmentation in echocardiography

Kaizhong Deng, Yanda Meng, Dongxu Gao, Joshua Bridge, Yaochun Shen, Gregory Y. H. Lip, Yitian Zhao, Yalin Zheng*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Echocardiography is an essential diagnostic method to assess cardiac functions. However, manually labelling the left ventricle region on echocardiography images is time-consuming and subject to observer bias. Therefore, it is vital to develop a high-performance and efficient automatic assessment tool. Inspired by the success of the transformer structure in vision tasks, we develop a lightweight model named ‘TransBridge’ for segmentation tasks. This hybrid framework combines a convolutional neural network (CNN) encoder-decoder structure and a transformer structure. The transformer layers bridge the CNN encoder and decoder to fuse the multi-level features extracted by the CNN encoder, to build global and inter-level dependencies. A new patch embedding layer has been implemented using the dense patch division method and shuffled group convolution to reduce the excessive parameter number in the embedding layer and the size of the token sequence. The model is evaluated on the EchoNet-Dynamic dataset for the left ventricle segmentation task. The experimental results show that the total number of parameters is reduced by 78.7% compared to CoTr and the Dice coefficient reaches 91.4%, proving the structure’s effectiveness.
Original languageEnglish
Title of host publicationSimplifying Medical Ultrasound. ASMUS 2021
Subtitle of host publicationSecond International Workshop, ASMUS 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings
EditorsJ. Alison Noble, Stephen Aylward, Alexander Grimwood, Zhe Min, Su-Lin Lee, Yipeng Hu
PublisherSpringer
Pages63-72
Number of pages10
ISBN (Electronic)9783030875831
ISBN (Print)9783030875824
DOIs
Publication statusPublished - 21 Sept 2021
EventASMUS 2021: Second International Workshop on Advances in Simplifying Medical Ultrasound - Strasbourg, France
Duration: 27 Sept 202127 Sept 2021

Publication series

NameLecture Notes in Computer Science (part of the Image Processing, Computer Vision, Pattern Recognition, and Graphics sub series)
PublisherSpringer
Volume12967
ISSN (Print)0302-9743

Conference

ConferenceASMUS 2021: Second International Workshop on Advances in Simplifying Medical Ultrasound
Country/TerritoryFrance
CityStrasbourg
Period27/09/2127/09/21

Keywords

  • echocardiography
  • left ventricle segmentation
  • lightweight transformer model
  • parameter efficiency

Fingerprint

Dive into the research topics of 'TransBridge: a lightweight transformer for left ventricle segmentation in echocardiography'. Together they form a unique fingerprint.

Cite this