Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network
The segmentation of the left ventricle (LV) is one of the fundamental procedures that must be performed to obtain quantitative measures of the heart, such as its volume, area, and ejection fraction. In clinical practice, the delineation of LV is still often conducted semi-automatically, leaving it o...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Life |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-1729/13/1/124 |
_version_ | 1797439677891870720 |
---|---|
author | Muhammad Ali Shoaib Joon Huang Chuah Raza Ali Samiappan Dhanalakshmi Yan Chai Hum Azira Khalil Khin Wee Lai |
author_facet | Muhammad Ali Shoaib Joon Huang Chuah Raza Ali Samiappan Dhanalakshmi Yan Chai Hum Azira Khalil Khin Wee Lai |
author_sort | Muhammad Ali Shoaib |
collection | DOAJ |
description | The segmentation of the left ventricle (LV) is one of the fundamental procedures that must be performed to obtain quantitative measures of the heart, such as its volume, area, and ejection fraction. In clinical practice, the delineation of LV is still often conducted semi-automatically, leaving it open to operator subjectivity. The automatic LV segmentation from echocardiography images is a challenging task due to poorly defined boundaries and operator dependency. Recent research has demonstrated that deep learning has the capability to employ the segmentation process automatically. However, the well-known state-of-the-art segmentation models still lack in terms of accuracy and speed. This study aims to develop a single-stage lightweight segmentation model that precisely and rapidly segments the LV from 2D echocardiography images. In this research, a backbone network is used to acquire both low-level and high-level features. Two parallel blocks, known as the spatial feature unit and the channel feature unit, are employed for the enhancement and improvement of these features. The refined features are merged by an integrated unit to segment the LV. The performance of the model and the time taken to segment the LV are compared to other established segmentation models, DeepLab, FCN, and Mask RCNN. The model achieved the highest values of the dice similarity index (0.9446), intersection over union (0.8445), and accuracy (0.9742). The evaluation metrics and processing time demonstrate that the proposed model not only provides superior quantitative results but also trains and segments the LV in less time, indicating its improved performance over competing segmentation models. |
first_indexed | 2024-03-09T11:56:33Z |
format | Article |
id | doaj.art-62531746e324448098c64c934303dae3 |
institution | Directory Open Access Journal |
issn | 2075-1729 |
language | English |
last_indexed | 2024-03-09T11:56:33Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Life |
spelling | doaj.art-62531746e324448098c64c934303dae32023-11-30T23:08:21ZengMDPI AGLife2075-17292023-01-0113112410.3390/life13010124Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural NetworkMuhammad Ali Shoaib0Joon Huang Chuah1Raza Ali2Samiappan Dhanalakshmi3Yan Chai Hum4Azira Khalil5Khin Wee Lai6Department of Electrical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur 50603, MalaysiaDepartment of Electrical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur 50603, MalaysiaDepartment of Electrical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur 50603, MalaysiaDepartment of Electronics and Communication Engineering, SRM Institute of Science and Technology, Kattankulathur 603203, IndiaDepartment of Mechatronics and Biomedical Engineering (DMBE), Lee Kong Chian Faculty of Engineering and Science (LKC FES), Universiti Tunku Abdul Rahman (UTAR), Jalan Sungai Long, Bandar Sungai Long, Cheras, Kajang 43000, MalaysiaFaculty of Science and Technology, Universiti Sains Islam Malaysia (USIM), Nilai 71800, MalaysiaDepartment of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur 50603, MalaysiaThe segmentation of the left ventricle (LV) is one of the fundamental procedures that must be performed to obtain quantitative measures of the heart, such as its volume, area, and ejection fraction. In clinical practice, the delineation of LV is still often conducted semi-automatically, leaving it open to operator subjectivity. The automatic LV segmentation from echocardiography images is a challenging task due to poorly defined boundaries and operator dependency. Recent research has demonstrated that deep learning has the capability to employ the segmentation process automatically. However, the well-known state-of-the-art segmentation models still lack in terms of accuracy and speed. This study aims to develop a single-stage lightweight segmentation model that precisely and rapidly segments the LV from 2D echocardiography images. In this research, a backbone network is used to acquire both low-level and high-level features. Two parallel blocks, known as the spatial feature unit and the channel feature unit, are employed for the enhancement and improvement of these features. The refined features are merged by an integrated unit to segment the LV. The performance of the model and the time taken to segment the LV are compared to other established segmentation models, DeepLab, FCN, and Mask RCNN. The model achieved the highest values of the dice similarity index (0.9446), intersection over union (0.8445), and accuracy (0.9742). The evaluation metrics and processing time demonstrate that the proposed model not only provides superior quantitative results but also trains and segments the LV in less time, indicating its improved performance over competing segmentation models.https://www.mdpi.com/2075-1729/13/1/124left ventricledeep learningspatial featureschannel features |
spellingShingle | Muhammad Ali Shoaib Joon Huang Chuah Raza Ali Samiappan Dhanalakshmi Yan Chai Hum Azira Khalil Khin Wee Lai Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network Life left ventricle deep learning spatial features channel features |
title | Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network |
title_full | Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network |
title_fullStr | Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network |
title_full_unstemmed | Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network |
title_short | Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network |
title_sort | fully automatic left ventricle segmentation using bilateral lightweight deep neural network |
topic | left ventricle deep learning spatial features channel features |
url | https://www.mdpi.com/2075-1729/13/1/124 |
work_keys_str_mv | AT muhammadalishoaib fullyautomaticleftventriclesegmentationusingbilaterallightweightdeepneuralnetwork AT joonhuangchuah fullyautomaticleftventriclesegmentationusingbilaterallightweightdeepneuralnetwork AT razaali fullyautomaticleftventriclesegmentationusingbilaterallightweightdeepneuralnetwork AT samiappandhanalakshmi fullyautomaticleftventriclesegmentationusingbilaterallightweightdeepneuralnetwork AT yanchaihum fullyautomaticleftventriclesegmentationusingbilaterallightweightdeepneuralnetwork AT azirakhalil fullyautomaticleftventriclesegmentationusingbilaterallightweightdeepneuralnetwork AT khinweelai fullyautomaticleftventriclesegmentationusingbilaterallightweightdeepneuralnetwork |