Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR Images
Due to institutional and privacy issues, medical imaging researches are confronted with serious data scarcity. Image synthesis using generative adversarial networks provides a generic solution to the lack of medical imaging data. We synthesize high-quality brain tumor-segmented MR images, which cons...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2020-01-01
|
Series: | Mathematical Problems in Engineering |
Online Access: | http://dx.doi.org/10.1155/2020/8273173 |
id |
doaj-25e2a38a1df24d9a8a5b0f0fdd9e811c |
---|---|
record_format |
Article |
spelling |
doaj-25e2a38a1df24d9a8a5b0f0fdd9e811c2020-11-25T03:15:08ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472020-01-01202010.1155/2020/82731738273173Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR ImagesHyunhee Lee0Jaechoon Jo1Heuiseok Lim2Department of Computer Science and Engineering, Korea University, Seoul 02841, Republic of KoreaDivision of Computer Engineering, College of Information Technology, Hanshin University, Osan-si 18101, Republic of KoreaDepartment of Computer Science and Engineering, Korea University, Seoul 02841, Republic of KoreaDue to institutional and privacy issues, medical imaging researches are confronted with serious data scarcity. Image synthesis using generative adversarial networks provides a generic solution to the lack of medical imaging data. We synthesize high-quality brain tumor-segmented MR images, which consists of two tasks: synthesis and segmentation. We performed experiments with two different generative networks, the first using the ResNet model, which has significant advantages of style transfer, and the second, the U-Net model, one of the most powerful models for segmentation. We compare the performance of each model and propose a more robust model for synthesizing brain tumor-segmented MR images. Although ResNet produced better-quality images than did U-Net for the same samples, it used a great deal of memory and took much longer to train. U-Net, meanwhile, segmented the brain tumors more accurately than did ResNet.http://dx.doi.org/10.1155/2020/8273173 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hyunhee Lee Jaechoon Jo Heuiseok Lim |
spellingShingle |
Hyunhee Lee Jaechoon Jo Heuiseok Lim Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR Images Mathematical Problems in Engineering |
author_facet |
Hyunhee Lee Jaechoon Jo Heuiseok Lim |
author_sort |
Hyunhee Lee |
title |
Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR Images |
title_short |
Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR Images |
title_full |
Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR Images |
title_fullStr |
Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR Images |
title_full_unstemmed |
Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR Images |
title_sort |
study on optimal generative network for synthesizing brain tumor-segmented mr images |
publisher |
Hindawi Limited |
series |
Mathematical Problems in Engineering |
issn |
1024-123X 1563-5147 |
publishDate |
2020-01-01 |
description |
Due to institutional and privacy issues, medical imaging researches are confronted with serious data scarcity. Image synthesis using generative adversarial networks provides a generic solution to the lack of medical imaging data. We synthesize high-quality brain tumor-segmented MR images, which consists of two tasks: synthesis and segmentation. We performed experiments with two different generative networks, the first using the ResNet model, which has significant advantages of style transfer, and the second, the U-Net model, one of the most powerful models for segmentation. We compare the performance of each model and propose a more robust model for synthesizing brain tumor-segmented MR images. Although ResNet produced better-quality images than did U-Net for the same samples, it used a great deal of memory and took much longer to train. U-Net, meanwhile, segmented the brain tumors more accurately than did ResNet. |
url |
http://dx.doi.org/10.1155/2020/8273173 |
work_keys_str_mv |
AT hyunheelee studyonoptimalgenerativenetworkforsynthesizingbraintumorsegmentedmrimages AT jaechoonjo studyonoptimalgenerativenetworkforsynthesizingbraintumorsegmentedmrimages AT heuiseoklim studyonoptimalgenerativenetworkforsynthesizingbraintumorsegmentedmrimages |
_version_ |
1715267182280048640 |