TY - JOUR
T1 - Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR Images
AU - Lee, Hyunhee
AU - Jo, Jaechoon
AU - Lim, Heuiseok
AU - Lee, Sanghyuk
N1 - Funding Information:
(is research was supported by the Ministry of Science and ICT (MSIT), Korea, under the Information Technology Research Center (ITRC) support program (IITP-2020-2018- 0-01405) supervised by the Institute for Information and Communications Technology Planning and Evaluation (IITP). (is work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (NRF-2017M3C4A7068189).
Publisher Copyright:
© 2020 Hyunhee Lee et al.
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85085992741&partnerID=8YFLogxK
U2 - 10.1155/2020/8273173
DO - 10.1155/2020/8273173
M3 - Article
AN - SCOPUS:85085992741
SN - 1024-123X
VL - 2020
JO - Mathematical Problems in Engineering
JF - Mathematical Problems in Engineering
M1 - 8273173
ER -