Publication:
Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network

Simple item page
dc.contributor.authorMuhammad Ali Shoaiben_US
dc.contributor.authorJoon Huang Chuahen_US
dc.contributor.authorRaza Alien_US
dc.contributor.authorSamiappan Dhanalakshmien_US
dc.contributor.authorYan Chai Humen_US
dc.contributor.authorAzira Khalilen_US
dc.contributor.authorKhin Wee Laien_US
dc.date.accessioned2024-05-29T02:28:15Z
dc.date.available2024-05-29T02:28:15Z
dc.date.issued2023
dc.date.submitted2023-5-31
dc.descriptionVolume 13, Issue 124 Page ( 1-14)en_US
dc.description.abstractThe 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.en_US
dc.identifier.citationShoaib, M.A.; Chuah, J.H.; Ali, R.; Dhanalakshmi, S.; Hum, Y.C.; Khalil, A.; Lai, K.W. Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network. Life 2023, 13, 124. https:// doi.org/10.3390/life13010124en_US
dc.identifier.doi10.3390/life13010124
dc.identifier.epage14
dc.identifier.issn2075-1729
dc.identifier.issue124
dc.identifier.spage1
dc.identifier.urihttps://www.mdpi.com/2075-1729/13/1/124
dc.identifier.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85146747824&origin=resultslist&sort=plf-f&src=s&sid=d1af16c2eba4f9ebe41802b9e98901d4&sot=b&sdt=b&s=TITLE-ABS-KEY%28Fully+Automatic+Left+Ventricle+Segmentation+Using+Bilateral+Lightweight+Deep+Neural+Network%29&sl=106&sessionSearchId=d1af16c2eba4f9ebe41802b9e98901d4&relpos=0
dc.identifier.urihttps://oarep.usim.edu.my/handle/123456789/10749
dc.identifier.volume13
dc.language.isoen_USen_US
dc.publisherMultidisciplinary Digital Publishing Instituteen_US
dc.relation.ispartofLifeen_US
dc.subjectleft ventricle; deep learning; spatial features; channel featuresen_US
dc.titleFully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Networken_US
dc.typeArticleen_US
dspace.entity.typePublication

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network.pdf
Size:
1.69 MB
Format:
Adobe Portable Document Format
Download

Collections

Scopus