Image Turing test and its applications on synthetic chest radiographs by using the progressive growing generative adversarial network
Miso Jang, Hyun‐Jin Bae, Minjee Kim, Seo Young Park, A Yeon Son, Se Jin Choi, Jooae Choe, Hye Young Choi, Hye Jeon Hwang, Han Na Noh, Joon Beom Seo, Sang Min Lee, Namkug Kim
Abstract
The generative adversarial network (GAN) is a promising deep learning method for generating images. We evaluated the generation of highly realistic and high-resolution chest radiographs (CXRs) using progressive growing GAN (PGGAN). We trained two PGGAN models using normal and abnormal CXRs, solely relying on normal CXRs to demonstrate the quality of synthetic CXRs that were 1000 × 1000 pixels in size. Image Turing tests were evaluated by six radiologists in a binary fashion using two independent validation sets to judge the authenticity of each CXR, with a mean accuracy of 67.42% and 69.92% for the first and second trials, respectively. Inter-reader agreements were poor for the first (κ = 0.10) and second (κ = 0.14) Turing tests. Additionally, a convolutional neural network (CNN) was used to classify normal or abnormal CXR using only real images and/or synthetic images mixed datasets. The accuracy of the CNN model trained using a mixed dataset of synthetic and real data was 93.3%, compared to 91.0% for the model built using only the real data. PGGAN was able to generate CXRs that were identical to real CXRs, and this showed promise to overcome imbalances between classes in CNN training.