Automatic Segmentation of the Left Ventricle in Apical Four-Chamber View on Transesophageal Echocardiography Based on UNeXt Deep Neural Network

<b>Background/Objectives:</b> The automatic left ventricle segmentation in transesophageal echocardiography (TEE) is of significant importance. In this paper, we constructed a large-scale TEE apical four-chamber view (A4CV) image dataset and proposed an automatic left ventricular segment...

Full description

Saved in:
Bibliographic Details
Main Authors: Lingeer Wu, Yijun Ling, Ling Lan, Kai He, Chunhua Yu, Zhuhuang Zhou, Le Shen
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/23/2766
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124319123439616
author Lingeer Wu
Yijun Ling
Ling Lan
Kai He
Chunhua Yu
Zhuhuang Zhou
Le Shen
author_facet Lingeer Wu
Yijun Ling
Ling Lan
Kai He
Chunhua Yu
Zhuhuang Zhou
Le Shen
author_sort Lingeer Wu
collection DOAJ
description <b>Background/Objectives:</b> The automatic left ventricle segmentation in transesophageal echocardiography (TEE) is of significant importance. In this paper, we constructed a large-scale TEE apical four-chamber view (A4CV) image dataset and proposed an automatic left ventricular segmentation method for the TEE A4CV based on the UNeXt deep neural network. <b>Methods:</b> UNeXt, a variant of U-Net integrating a multilayer perceptron, was employed for left ventricle segmentation in the TEE A4CV because it could yield promising segmentation performance while reducing both the number of network parameters and computational complexity. We also compared the proposed method with U-Net, TransUNet, and Attention U-Net models. Standard TEE A4CV videos were collected from 60 patients undergoing cardiac surgery, from the onset of anesthesia to the conclusion of the procedure. After preprocessing, a dataset comprising 3000 TEE images and their corresponding labels was generated. The dataset was randomly divided into training, validation, and test sets in an 8:1:1 ratio on the patient level. The training and validation sets were used to train the UNeXt, U-Net, TransUNet, and Attention U-Net models for left ventricular segmentation. The dice similarity coefficient (DSC) and Intersection over Union (IoU) were used to evaluate the segmentation performance of each model, and the Kruskal–Wallis test was employed to analyze the significance of DSC differences. <b>Results:</b> On the test set, the UNeXt model achieved an average DSC of 88.60%, outperforming U-Net (87.76%), TransUNet (85.75%, <i>p</i> < 0.05), and Attention U-Net (79.98%; <i>p</i> < 0.05). Additionally, the UNeXt model had a smaller number of parameters (1.47 million) and floating point operations (2.28 giga) as well as a shorter average inference time per image (141.73 ms), compared to U-Net (185.12 ms), TransUNet (209.08 ms), and Attention U-Net (201.13 ms). The average IoU of UNeXt (77.60%) was also higher than that of U-Net (76.61%), TransUNet (77.35%), and Attention U-Net (68.86%). <b>Conclusions:</b> This study pioneered the construction of a large-scale TEE A4CV dataset and the application of UNeXt to left ventricle segmentation in the TEE A4CV. The proposed method may be used for automatic segmentation of the left ventricle in the TEE A4CV.
format Article
id doaj-art-ceeecd9fd4c04423b85ef97fc3b27404
institution Kabale University
issn 2075-4418
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-ceeecd9fd4c04423b85ef97fc3b274042024-12-13T16:24:58ZengMDPI AGDiagnostics2075-44182024-12-011423276610.3390/diagnostics14232766Automatic Segmentation of the Left Ventricle in Apical Four-Chamber View on Transesophageal Echocardiography Based on UNeXt Deep Neural NetworkLingeer Wu0Yijun Ling1Ling Lan2Kai He3Chunhua Yu4Zhuhuang Zhou5Le Shen6Department of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, ChinaDepartment of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, ChinaDepartment of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China<b>Background/Objectives:</b> The automatic left ventricle segmentation in transesophageal echocardiography (TEE) is of significant importance. In this paper, we constructed a large-scale TEE apical four-chamber view (A4CV) image dataset and proposed an automatic left ventricular segmentation method for the TEE A4CV based on the UNeXt deep neural network. <b>Methods:</b> UNeXt, a variant of U-Net integrating a multilayer perceptron, was employed for left ventricle segmentation in the TEE A4CV because it could yield promising segmentation performance while reducing both the number of network parameters and computational complexity. We also compared the proposed method with U-Net, TransUNet, and Attention U-Net models. Standard TEE A4CV videos were collected from 60 patients undergoing cardiac surgery, from the onset of anesthesia to the conclusion of the procedure. After preprocessing, a dataset comprising 3000 TEE images and their corresponding labels was generated. The dataset was randomly divided into training, validation, and test sets in an 8:1:1 ratio on the patient level. The training and validation sets were used to train the UNeXt, U-Net, TransUNet, and Attention U-Net models for left ventricular segmentation. The dice similarity coefficient (DSC) and Intersection over Union (IoU) were used to evaluate the segmentation performance of each model, and the Kruskal–Wallis test was employed to analyze the significance of DSC differences. <b>Results:</b> On the test set, the UNeXt model achieved an average DSC of 88.60%, outperforming U-Net (87.76%), TransUNet (85.75%, <i>p</i> < 0.05), and Attention U-Net (79.98%; <i>p</i> < 0.05). Additionally, the UNeXt model had a smaller number of parameters (1.47 million) and floating point operations (2.28 giga) as well as a shorter average inference time per image (141.73 ms), compared to U-Net (185.12 ms), TransUNet (209.08 ms), and Attention U-Net (201.13 ms). The average IoU of UNeXt (77.60%) was also higher than that of U-Net (76.61%), TransUNet (77.35%), and Attention U-Net (68.86%). <b>Conclusions:</b> This study pioneered the construction of a large-scale TEE A4CV dataset and the application of UNeXt to left ventricle segmentation in the TEE A4CV. The proposed method may be used for automatic segmentation of the left ventricle in the TEE A4CV.https://www.mdpi.com/2075-4418/14/23/2766transesophageal echocardiographyleft ventriclesegmentationdeep learning
spellingShingle Lingeer Wu
Yijun Ling
Ling Lan
Kai He
Chunhua Yu
Zhuhuang Zhou
Le Shen
Automatic Segmentation of the Left Ventricle in Apical Four-Chamber View on Transesophageal Echocardiography Based on UNeXt Deep Neural Network
Diagnostics
transesophageal echocardiography
left ventricle
segmentation
deep learning
title Automatic Segmentation of the Left Ventricle in Apical Four-Chamber View on Transesophageal Echocardiography Based on UNeXt Deep Neural Network
title_full Automatic Segmentation of the Left Ventricle in Apical Four-Chamber View on Transesophageal Echocardiography Based on UNeXt Deep Neural Network
title_fullStr Automatic Segmentation of the Left Ventricle in Apical Four-Chamber View on Transesophageal Echocardiography Based on UNeXt Deep Neural Network
title_full_unstemmed Automatic Segmentation of the Left Ventricle in Apical Four-Chamber View on Transesophageal Echocardiography Based on UNeXt Deep Neural Network
title_short Automatic Segmentation of the Left Ventricle in Apical Four-Chamber View on Transesophageal Echocardiography Based on UNeXt Deep Neural Network
title_sort automatic segmentation of the left ventricle in apical four chamber view on transesophageal echocardiography based on unext deep neural network
topic transesophageal echocardiography
left ventricle
segmentation
deep learning
url https://www.mdpi.com/2075-4418/14/23/2766
work_keys_str_mv AT lingeerwu automaticsegmentationoftheleftventricleinapicalfourchamberviewontransesophagealechocardiographybasedonunextdeepneuralnetwork
AT yijunling automaticsegmentationoftheleftventricleinapicalfourchamberviewontransesophagealechocardiographybasedonunextdeepneuralnetwork
AT linglan automaticsegmentationoftheleftventricleinapicalfourchamberviewontransesophagealechocardiographybasedonunextdeepneuralnetwork
AT kaihe automaticsegmentationoftheleftventricleinapicalfourchamberviewontransesophagealechocardiographybasedonunextdeepneuralnetwork
AT chunhuayu automaticsegmentationoftheleftventricleinapicalfourchamberviewontransesophagealechocardiographybasedonunextdeepneuralnetwork
AT zhuhuangzhou automaticsegmentationoftheleftventricleinapicalfourchamberviewontransesophagealechocardiographybasedonunextdeepneuralnetwork
AT leshen automaticsegmentationoftheleftventricleinapicalfourchamberviewontransesophagealechocardiographybasedonunextdeepneuralnetwork