Research Article
Data Augmentation for Cardiac Magnetic Resonance Image Using Evolutionary GAN
@INPROCEEDINGS{10.1007/978-3-030-77569-8_10, author={Ying Fu and Minxue Gong and Guang Yang and Jiliu Zhou}, title={Data Augmentation for Cardiac Magnetic Resonance Image Using Evolutionary GAN}, proceedings={Quality, Reliability, Security and Robustness in Heterogeneous Systems. 16th EAI International Conference, QShine 2020, Virtual Event, November 29--30, 2020, Proceedings}, proceedings_a={QSHINE}, year={2021}, month={6}, keywords={Evolutionary GAN Cardiac magnetic resonance Data augmentation Linear interpolation}, doi={10.1007/978-3-030-77569-8_10} }- Ying Fu
Minxue Gong
Guang Yang
Jiliu Zhou
Year: 2021
Data Augmentation for Cardiac Magnetic Resonance Image Using Evolutionary GAN
QSHINE
Springer
DOI: 10.1007/978-3-030-77569-8_10
Abstract
Generative adversarial networks (GAN) could synthesize semantically meaningful data from standard signal distribution, which make it have considerable potential to alleviate data scarcity. In this paper, based on Evolutionary GAN, cardiac magnetic resonance images enhancement method is proposed to solve over-fitting problem caused by training convolution network with small dataset. The most optimal generator which consider the quality and diversity of generated images simultaneously from many generator mutations is chosen. Meanwhile, to expand the whole training set distribution, we combine the linear interpolation of eigenvectors to synthesize new training samples and synthesize related linear interpolation labels, which can make the discrete sample space become continuous to improve the smoothness between domains. In this paper, the effectiveness of this method is verified by classification experiments, and the influence of the proportion of synthesized samples on the classification results of cardiac magnetic resonance images is explored.
