Cargando…

Breast Ultrasound Images Augmentation and Segmentation Using GAN with Identity Block and Modified U-Net 3+

One of the most prevalent diseases affecting women in recent years is breast cancer. Early breast cancer detection can help in the treatment, lower the infection risk, and worsen the results. This paper presents a hybrid approach for augmentation and segmenting breast cancer. The framework contains...

Descripción completa

Detalles Bibliográficos
Autores principales: Alruily, Meshrif, Said, Wael, Mostafa, Ayman Mohamed, Ezz, Mohamed, Elmezain, Mahmoud
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10610596/
https://www.ncbi.nlm.nih.gov/pubmed/37896692
http://dx.doi.org/10.3390/s23208599
_version_ 1785128294023168000
author Alruily, Meshrif
Said, Wael
Mostafa, Ayman Mohamed
Ezz, Mohamed
Elmezain, Mahmoud
author_facet Alruily, Meshrif
Said, Wael
Mostafa, Ayman Mohamed
Ezz, Mohamed
Elmezain, Mahmoud
author_sort Alruily, Meshrif
collection PubMed
description One of the most prevalent diseases affecting women in recent years is breast cancer. Early breast cancer detection can help in the treatment, lower the infection risk, and worsen the results. This paper presents a hybrid approach for augmentation and segmenting breast cancer. The framework contains two main stages: augmentation and segmentation of ultrasound images. The augmentation of the ultrasounds is applied using generative adversarial networks (GAN) with nonlinear identity block, label smoothing, and a new loss function. The segmentation of the ultrasounds applied a modified U-Net 3+. The hybrid approach achieves efficient results in the segmentation and augmentation steps compared with the other available methods for the same task. The modified version of the GAN with the nonlinear identity block overcomes different types of modified GAN in the ultrasound augmentation process, such as speckle GAN, UltraGAN, and deep convolutional GAN. The modified U-Net 3+ also overcomes the different architectures of U-Nets in the segmentation process. The GAN with nonlinear identity blocks achieved an inception score of 14.32 and a Fréchet inception distance of 41.86 in the augmenting process. The GAN with identity achieves a smaller value in Fréchet inception distance (FID) and a bigger value in inception score; these results prove the model’s efficiency compared with other versions of GAN in the augmentation process. The modified U-Net 3+ architecture achieved a Dice Score of 95.49% and an Accuracy of 95.67%.
format Online
Article
Text
id pubmed-10610596
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106105962023-10-28 Breast Ultrasound Images Augmentation and Segmentation Using GAN with Identity Block and Modified U-Net 3+ Alruily, Meshrif Said, Wael Mostafa, Ayman Mohamed Ezz, Mohamed Elmezain, Mahmoud Sensors (Basel) Article One of the most prevalent diseases affecting women in recent years is breast cancer. Early breast cancer detection can help in the treatment, lower the infection risk, and worsen the results. This paper presents a hybrid approach for augmentation and segmenting breast cancer. The framework contains two main stages: augmentation and segmentation of ultrasound images. The augmentation of the ultrasounds is applied using generative adversarial networks (GAN) with nonlinear identity block, label smoothing, and a new loss function. The segmentation of the ultrasounds applied a modified U-Net 3+. The hybrid approach achieves efficient results in the segmentation and augmentation steps compared with the other available methods for the same task. The modified version of the GAN with the nonlinear identity block overcomes different types of modified GAN in the ultrasound augmentation process, such as speckle GAN, UltraGAN, and deep convolutional GAN. The modified U-Net 3+ also overcomes the different architectures of U-Nets in the segmentation process. The GAN with nonlinear identity blocks achieved an inception score of 14.32 and a Fréchet inception distance of 41.86 in the augmenting process. The GAN with identity achieves a smaller value in Fréchet inception distance (FID) and a bigger value in inception score; these results prove the model’s efficiency compared with other versions of GAN in the augmentation process. The modified U-Net 3+ architecture achieved a Dice Score of 95.49% and an Accuracy of 95.67%. MDPI 2023-10-20 /pmc/articles/PMC10610596/ /pubmed/37896692 http://dx.doi.org/10.3390/s23208599 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Alruily, Meshrif
Said, Wael
Mostafa, Ayman Mohamed
Ezz, Mohamed
Elmezain, Mahmoud
Breast Ultrasound Images Augmentation and Segmentation Using GAN with Identity Block and Modified U-Net 3+
title Breast Ultrasound Images Augmentation and Segmentation Using GAN with Identity Block and Modified U-Net 3+
title_full Breast Ultrasound Images Augmentation and Segmentation Using GAN with Identity Block and Modified U-Net 3+
title_fullStr Breast Ultrasound Images Augmentation and Segmentation Using GAN with Identity Block and Modified U-Net 3+
title_full_unstemmed Breast Ultrasound Images Augmentation and Segmentation Using GAN with Identity Block and Modified U-Net 3+
title_short Breast Ultrasound Images Augmentation and Segmentation Using GAN with Identity Block and Modified U-Net 3+
title_sort breast ultrasound images augmentation and segmentation using gan with identity block and modified u-net 3+
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10610596/
https://www.ncbi.nlm.nih.gov/pubmed/37896692
http://dx.doi.org/10.3390/s23208599
work_keys_str_mv AT alruilymeshrif breastultrasoundimagesaugmentationandsegmentationusingganwithidentityblockandmodifiedunet3
AT saidwael breastultrasoundimagesaugmentationandsegmentationusingganwithidentityblockandmodifiedunet3
AT mostafaaymanmohamed breastultrasoundimagesaugmentationandsegmentationusingganwithidentityblockandmodifiedunet3
AT ezzmohamed breastultrasoundimagesaugmentationandsegmentationusingganwithidentityblockandmodifiedunet3
AT elmezainmahmoud breastultrasoundimagesaugmentationandsegmentationusingganwithidentityblockandmodifiedunet3