Cargando…

Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model

Prostate cancer remains a major health concern among elderly men. Deep learning is a state-of-the-art technique for MR image-based prostate cancer diagnosis, but one of major bottlenecks is the severe lack of annotated MR images. The traditional and Generative Adversarial Network (GAN)-based data au...

Descripción completa

Detalles Bibliográficos
Autores principales: Yu, Houqiang, Zhang, Xuming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7601698/
https://www.ncbi.nlm.nih.gov/pubmed/33050243
http://dx.doi.org/10.3390/s20205736
_version_ 1783603491990667264
author Yu, Houqiang
Zhang, Xuming
author_facet Yu, Houqiang
Zhang, Xuming
author_sort Yu, Houqiang
collection PubMed
description Prostate cancer remains a major health concern among elderly men. Deep learning is a state-of-the-art technique for MR image-based prostate cancer diagnosis, but one of major bottlenecks is the severe lack of annotated MR images. The traditional and Generative Adversarial Network (GAN)-based data augmentation methods cannot ensure the quality and the diversity of generated training samples. In this paper, we have proposed a novel GAN model for synthesis of MR images by utilizing its powerful ability in modeling the complex data distributions. The proposed model is designed based on the architecture of deep convolutional GAN. To learn the more equivariant representation of images that is robust to the changes in the pose and spatial relationship of objects in the images, the capsule network is applied to replace CNN used in the discriminator of regular GAN. Meanwhile, the least squares loss has been adopted for both the generator and discriminator in the proposed GAN to address the vanishing gradient problem of sigmoid cross entropy loss function in regular GAN. Extensive experiments are conducted on the simulated and real MR images. The results demonstrate that the proposed capsule network-based GAN model can generate more realistic and higher quality MR images than the compared GANs. The quantitative comparisons show that among all evaluated models, the proposed GAN generally achieves the smallest Kullback–Leibler divergence values for image generation task and provides the best classification performance when it is introduced into the deep learning method for image classification task.
format Online
Article
Text
id pubmed-7601698
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-76016982020-11-01 Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model Yu, Houqiang Zhang, Xuming Sensors (Basel) Article Prostate cancer remains a major health concern among elderly men. Deep learning is a state-of-the-art technique for MR image-based prostate cancer diagnosis, but one of major bottlenecks is the severe lack of annotated MR images. The traditional and Generative Adversarial Network (GAN)-based data augmentation methods cannot ensure the quality and the diversity of generated training samples. In this paper, we have proposed a novel GAN model for synthesis of MR images by utilizing its powerful ability in modeling the complex data distributions. The proposed model is designed based on the architecture of deep convolutional GAN. To learn the more equivariant representation of images that is robust to the changes in the pose and spatial relationship of objects in the images, the capsule network is applied to replace CNN used in the discriminator of regular GAN. Meanwhile, the least squares loss has been adopted for both the generator and discriminator in the proposed GAN to address the vanishing gradient problem of sigmoid cross entropy loss function in regular GAN. Extensive experiments are conducted on the simulated and real MR images. The results demonstrate that the proposed capsule network-based GAN model can generate more realistic and higher quality MR images than the compared GANs. The quantitative comparisons show that among all evaluated models, the proposed GAN generally achieves the smallest Kullback–Leibler divergence values for image generation task and provides the best classification performance when it is introduced into the deep learning method for image classification task. MDPI 2020-10-09 /pmc/articles/PMC7601698/ /pubmed/33050243 http://dx.doi.org/10.3390/s20205736 Text en © 2020 by the authors. 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 (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yu, Houqiang
Zhang, Xuming
Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model
title Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model
title_full Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model
title_fullStr Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model
title_full_unstemmed Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model
title_short Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model
title_sort synthesis of prostate mr images for classification using capsule network-based gan model
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7601698/
https://www.ncbi.nlm.nih.gov/pubmed/33050243
http://dx.doi.org/10.3390/s20205736
work_keys_str_mv AT yuhouqiang synthesisofprostatemrimagesforclassificationusingcapsulenetworkbasedganmodel
AT zhangxuming synthesisofprostatemrimagesforclassificationusingcapsulenetworkbasedganmodel