Unsupervised Image Segmentation on 2D Echocardiogram

Echocardiography is a widely used, non-invasive imaging technique for diagnosing and monitoring heart conditions. However, accurate segmentation of cardiac structures, particularly the left ventricle, remains a complex task due to the inherent variability and noise in echocardiographic images. Curre...

Full description

Saved in:
Bibliographic Details
Main Authors: Gabriel Farias Cacao, Dongping Du, Nandini Nair
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/17/11/515
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154666184802304
author Gabriel Farias Cacao
Dongping Du
Nandini Nair
author_facet Gabriel Farias Cacao
Dongping Du
Nandini Nair
author_sort Gabriel Farias Cacao
collection DOAJ
description Echocardiography is a widely used, non-invasive imaging technique for diagnosing and monitoring heart conditions. However, accurate segmentation of cardiac structures, particularly the left ventricle, remains a complex task due to the inherent variability and noise in echocardiographic images. Current supervised models have achieved state-of-the-art results but are highly dependent on large, annotated datasets, which are costly and time-consuming to obtain and depend on the quality of the annotated data. These limitations motivate the need for unsupervised methods that can generalize across different image conditions without relying on annotated data. In this study, we propose an unsupervised approach for segmenting 2D echocardiographic images. By combining customized objective functions with convolutional neural networks (CNNs), our method effectively segments cardiac structures, addressing the challenges posed by low-resolution and gray-scale images. Our approach leverages techniques traditionally used outside of medical imaging, optimizing feature extraction through CNNs in a data-driven manner and with a new and smaller network design. Another key contribution of this work is the introduction of a post-processing algorithm that refines the segmentation to isolate the left ventricle in both diastolic and systolic positions, enabling the calculation of the ejection fraction (EF). This calculation serves as a benchmark for evaluating the performance of our unsupervised method. Our results demonstrate the potential of unsupervised learning to improve echocardiogram analysis by overcoming the limitations of supervised approaches, particularly in settings where labeled data are scarce or unavailable.
format Article
id doaj-art-0368181588d44fa5bbf7db6d8349075d
institution Kabale University
issn 1999-4893
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-0368181588d44fa5bbf7db6d8349075d2024-11-26T17:45:28ZengMDPI AGAlgorithms1999-48932024-11-01171151510.3390/a17110515Unsupervised Image Segmentation on 2D EchocardiogramGabriel Farias Cacao0Dongping Du1Nandini Nair2Department of Industrial, Manufacturing, and Systems Engineering (IMSE), Texas Tech University, Lubbock, TX 79409, USADepartment of Industrial, Manufacturing, and Systems Engineering (IMSE), Texas Tech University, Lubbock, TX 79409, USAPennState College of Medicine, Heart and Vascular Institute, Milton S. Hershey Medical Center, 500 University Dr, Hershey, PA 17033, USAEchocardiography is a widely used, non-invasive imaging technique for diagnosing and monitoring heart conditions. However, accurate segmentation of cardiac structures, particularly the left ventricle, remains a complex task due to the inherent variability and noise in echocardiographic images. Current supervised models have achieved state-of-the-art results but are highly dependent on large, annotated datasets, which are costly and time-consuming to obtain and depend on the quality of the annotated data. These limitations motivate the need for unsupervised methods that can generalize across different image conditions without relying on annotated data. In this study, we propose an unsupervised approach for segmenting 2D echocardiographic images. By combining customized objective functions with convolutional neural networks (CNNs), our method effectively segments cardiac structures, addressing the challenges posed by low-resolution and gray-scale images. Our approach leverages techniques traditionally used outside of medical imaging, optimizing feature extraction through CNNs in a data-driven manner and with a new and smaller network design. Another key contribution of this work is the introduction of a post-processing algorithm that refines the segmentation to isolate the left ventricle in both diastolic and systolic positions, enabling the calculation of the ejection fraction (EF). This calculation serves as a benchmark for evaluating the performance of our unsupervised method. Our results demonstrate the potential of unsupervised learning to improve echocardiogram analysis by overcoming the limitations of supervised approaches, particularly in settings where labeled data are scarce or unavailable.https://www.mdpi.com/1999-4893/17/11/515unsupervised learningimage segmentationechocardiographyconvolutional neural networksmedical imaging
spellingShingle Gabriel Farias Cacao
Dongping Du
Nandini Nair
Unsupervised Image Segmentation on 2D Echocardiogram
Algorithms
unsupervised learning
image segmentation
echocardiography
convolutional neural networks
medical imaging
title Unsupervised Image Segmentation on 2D Echocardiogram
title_full Unsupervised Image Segmentation on 2D Echocardiogram
title_fullStr Unsupervised Image Segmentation on 2D Echocardiogram
title_full_unstemmed Unsupervised Image Segmentation on 2D Echocardiogram
title_short Unsupervised Image Segmentation on 2D Echocardiogram
title_sort unsupervised image segmentation on 2d echocardiogram
topic unsupervised learning
image segmentation
echocardiography
convolutional neural networks
medical imaging
url https://www.mdpi.com/1999-4893/17/11/515
work_keys_str_mv AT gabrielfariascacao unsupervisedimagesegmentationon2dechocardiogram
AT dongpingdu unsupervisedimagesegmentationon2dechocardiogram
AT nandininair unsupervisedimagesegmentationon2dechocardiogram