Please use this identifier to cite or link to this item: http://hdl.handle.net/10995/102849
Title: Generation of echocardiographic 2D images of the heart using cGAN
Authors: Zyuzin, V.
Komleva, J.
Porshnev, S.
Issue Date: 2021
Publisher: IOP Publishing Ltd
Citation: Zyuzin V. Generation of echocardiographic 2D images of the heart using cGAN / V. Zyuzin, J. Komleva, S. Porshnev. — DOI 10.1088/1742-6596/1727/1/012013 // Journal of Physics: Conference Series. — 2021. — Vol. 1727. — Iss. 1. — 012013.
Abstract: One of the most significant tasks of echocardiography is the automatic delineation of the cardiac structures from 2D echocardiographic images. Over the past decades, the automation of this taskhas been the subject of intense research. One of the most effective approaches is based on the deepconvolutional neural networks. Nonetheless, it is necessary to use echocardiogram frames of the cardiac muscle, which show the boundaries of the cardiac structures labeled/annotated by experts/cardiologists to train it. However, the number of databases containing the necessary information is relatively small. Therefore, generated echocardiogram frames are used to increase the amount of training samples. This process is based on the ultrasound images of the heart, annotated by experts. The article proposes an improved method for generating echocardiograms using a generative adversarial neural network (GAN) with a patch-based conditional discriminator. It has been demonstrated that it is possible to improve the quality of generated echocardiogram frames in both two and four chamber views (AP4C, AP2C) using the masks of cardiac segmentation with sub-pixel convolution layer (pixel shuffle). It is demonstrated that the proposed approach makes it possible to generate ultrasound images, the structure of which corresponds to the specified segmentation masks. It is expected that this method will improve the accuracy of solving the direct problem of automatic segmentation of the left ventricle. © Published under licence by IOP Publishing Ltd.
Keywords: BIG DATA
ECHOCARDIOGRAPHY
HEART
MUSCLE
NEURAL NETWORKS
PIXELS
ULTRASONICS
AUTOMATIC SEGMENTATIONS
CARDIAC SEGMENTATION
CARDIAC STRUCTURE
DIRECT PROBLEMS
ECHOCARDIOGRAPHIC IMAGES
EFFECTIVE APPROACHES
SEGMENTATION MASKS
ULTRASOUND IMAGES
IMAGE SEGMENTATION
URI: http://hdl.handle.net/10995/102849
Access: info:eu-repo/semantics/openAccess
SCOPUS ID: 85101711342
PURE ID: 21021844
6829cc0f-bf8c-4f03-a4db-e2077fc6ea5c
ISSN: 17426588
DOI: 10.1088/1742-6596/1727/1/012013
Appears in Collections:Научные публикации, проиндексированные в SCOPUS и WoS CC

Files in This Item:
File Description SizeFormat 
2-s2.0-85101711342.pdf857,01 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.