Creation of synthetic contrast-enhanced computed tomography images using deep neural networks to screen for renal cell carcinoma

Objectives: To elucidate if synthetic contrast enhanced computed tomography (CECT) images created from plain CT images using deep neural networks (DNN) could be used for screening, clinical diagnosis, and postoperative follow up of small diameter renal tumors by comparing the concordance rate between real and synthetic CECT images and the diagnoses according to 10 urologists. Methods: This retrospective, multicenter study included 155 patients (artificial intelligence training cohort [n=99], validation cohort [n=56]) who underwent surgery for small-diameter (≤40 mm) renal tumors, with the pathological diagnosis of renal cell carcinoma, during 2010 to 2020. Preoperatively, dynamic plain CT and CECT images were obtained. We created a learned DNN using pix2pix. We examined the quality of the synthetic CECT images created using this DNN and compared them with real CECT images using the zero mean normalized cross correlation parameter. We assessed concordance rates between real and synthetic images and diagnoses according to 10 urologists by creating a receiver operating characteristic curve and calculating the area under the curve (AUC). Results: The synthetic CECT images were highly concordant with the real CECT images, regardless of the existence or morphology of the renal tumor. Regarding the concordance rate, a greater AUC was obtained with synthetic CECT (AUC=0.892) than with only CT (AUC=0.720; p<0.001). Conclusions: This study is the first to use DNN to create a high-quality synthetic CECT image that was highly concordant with a real CECT image. Synthetic CECT images could be used for urological diagnoses and clinical screening.