TY - JOUR
T1 - COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network
AU - Jiang, Yifan
AU - Chen, Han
AU - Loew, Murray
AU - Ko, Hanseok
N1 - Funding Information:
Manuscript received July 21, 2020; revised September 25, 2020 and November 8, 2020; accepted December 1, 2020. Date of publication December 4, 2020; date of current version February 4, 2021. This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea Government (MSIT) under Grant 2019R1A2C2009480. (Corresponding author: Hanseok Ko.) Yifan Jiang, Han Chen, and Hanseok Ko are with the School of Electrical Engineering, Korea University, Seoul 02841, South Korea (e-mail: yfjiang@ispl.korea.ac.kr; hanchen@ispl.korea.ac.kr; hsko@korea.ac.kr).
Publisher Copyright:
© 2013 IEEE.
PY - 2021/2
Y1 - 2021/2
N2 - Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic that has spread rapidly since December 2019. Real-time reverse transcription polymerase chain reaction (rRT-PCR) and chest computed tomography (CT) imaging both play an important role in COVID-19 diagnosis. Chest CT imaging offers the benefits of quick reporting, a low cost, and high sensitivity for the detection of pulmonary infection. Recently, deep-learning-based computer vision methods have demonstrated great promise for use in medical imaging applications, including X-rays, magnetic resonance imaging, and CT imaging. However, training a deep-learning model requires large volumes of data, and medical staff faces a high risk when collecting COVID-19 CT data due to the high infectivity of the disease. Another issue is the lack of experts available for data labeling. In order to meet the data requirements for COVID-19 CT imaging, we propose a CT image synthesis approach based on a conditional generative adversarial network that can effectively generate high-quality and realistic COVID-19 CT images for use in deep-learning-based medical imaging tasks. Experimental results show that the proposed method outperforms other state-of-the-art image synthesis methods with the generated COVID-19 CT images and indicates promising for various machine learning applications including semantic segmentation and classification.
AB - Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic that has spread rapidly since December 2019. Real-time reverse transcription polymerase chain reaction (rRT-PCR) and chest computed tomography (CT) imaging both play an important role in COVID-19 diagnosis. Chest CT imaging offers the benefits of quick reporting, a low cost, and high sensitivity for the detection of pulmonary infection. Recently, deep-learning-based computer vision methods have demonstrated great promise for use in medical imaging applications, including X-rays, magnetic resonance imaging, and CT imaging. However, training a deep-learning model requires large volumes of data, and medical staff faces a high risk when collecting COVID-19 CT data due to the high infectivity of the disease. Another issue is the lack of experts available for data labeling. In order to meet the data requirements for COVID-19 CT imaging, we propose a CT image synthesis approach based on a conditional generative adversarial network that can effectively generate high-quality and realistic COVID-19 CT images for use in deep-learning-based medical imaging tasks. Experimental results show that the proposed method outperforms other state-of-the-art image synthesis methods with the generated COVID-19 CT images and indicates promising for various machine learning applications including semantic segmentation and classification.
KW - COVID-19
KW - computed topography
KW - conditional generative adversarial network
KW - image synthesis
UR - http://www.scopus.com/inward/record.url?scp=85097960653&partnerID=8YFLogxK
U2 - 10.1109/JBHI.2020.3042523
DO - 10.1109/JBHI.2020.3042523
M3 - Article
C2 - 33275588
AN - SCOPUS:85097960653
VL - 25
SP - 441
EP - 452
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
SN - 2168-2194
IS - 2
M1 - 9281375
ER -