Clinical ultra-high resolution CT scans enabled by using a generative adversarial network.

Abstract

Ultra-high resolution computed tomography (UHRCT) has shown great potential for the detection of pulmonary diseases. However, UHRCT scanning generally induces increases in scanning time and radiation exposure. Super resolution is a gradually prosperous application in CT imaging despite higher radiation dose. Recent works have proved that the convolution neural network especially the generative adversarial network (GAN) based model could generate high-resolution CT using phantom images or simulated low resolution data without extra dose. Research that used clinical CT particularly lung images are rare due to the difficulty in collecting paired dataset. To generate clinical UHRCT in lung from low resolution computed tomography (LRCT) using a GAN model. 43 clinical scans with LRCT and UHRCT were collected in this study. Paired patches were selected using the structural similarity index measure (SSIM) and the peak signal-to-noise ratio (PSNR) threshold. A relativistic GAN with gradient guidance was trained to learn the mapping from LRCT to UHRCT. The performance of the proposed method was evaluated using PSNR and SSIM. A reader study with five-point Likert score (five for the worst and one for the best) is also applied to assess the proposed method in terms of general quality, diagnostic confidence, sharpness and denoise level. Experimental results show that our method got PSNR 32.60±2.92 and SSIM 0.881±0.057 on our clinical CT dataset, outperforming other state-of-the-art methods based on the simulated scenarios. Moreover, reader study shows that our method reached the good clinical performance in terms of general quality (1.14±0.36), diagnostic confidence (1.36±0.49), sharpness (1.07±0.27) and high denoise level (1.29±0.61) compared to other SR methods. This study demonstrated the feasibility of generating UHRCT images from LRCT without longer scanning time or increased radiation dose.