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

In this study, we elucidate if synthetic contrast enhanced computed tomography images created from plain computed tomography images using deep neural networks could be used for screening, clinical diagnosis, and postoperative follow-up of small-diameter renal tumors. 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 2010-2020. We created a learned deep neural networks using pix2pix. We examined the quality of the synthetic enhanced computed tomography images created using this deep neural networks and compared them with real enhanced computed tomography 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. The synthetic computed tomography images were highly concordant with the real computed tomography images, regardless of the existence or morphology of the renal tumor. Regarding the concordance rate, a greater area under the curve was obtained with synthetic computed tomography (area under the curve = 0.892) than with only computed tomography (area under the curve = 0.720; p < 0.001). In conclusions, this study is the first to use deep neural networks to create a high-quality synthetic computed tomography image that was highly concordant with a real computed tomography image. Our synthetic computed tomography images could be used for urological diagnoses and clinical screening.

Characteristics of uroflowmetry patterns in men with detrusor underactivity revealed by artificial intelligence.

OBJECTIVES: To elucidate the characteristics of uroflowmetry (UFM) observed in men with detrusor underactivity (DU) using our developed artificial intelligence (AI) diagnostic algorithm to distinguish between DU and bladder outlet obstruction (BOO). METHODS: Subjective and objective parameters, including four UFM parameters (first peak flow rate, time to first peak, gradient to first peak, and the ratio of first peak flow rate to maximum flow rate [Qmax ]) selected by analyzing the judgment basis of the AI diagnostic system, were compared in 266 treatment-naive men with lower urinary tract symptoms (LUTS). Patients were divided into the DU (70; 26.32%) and non-DU (196; 73.68%) groups, and the UFM parameters for predicting the presence of DU were determined by multivariate analysis and receiver operating characteristic (ROC) curve analysis. Detrusor underactivity was defined as a bladder contractility index <100 and a BOO index <40. RESULTS: Most parameters on the first peak flow of UFM were significantly lower in the DU group. On multivariate analysis, lower first peak flow rate and lower ratio of first peak flow rate to Qmax were significant parameters to predict DU. In the ROC analysis, the ratio of the first peak flow rate to Qmax showed the highest area under the curve (0.848) and yielded sensitivities of 76% and specificities of 83% for DU diagnosis, with cutoff values of 0.8. CONCLUSIONS: Parameters on the first peak flow of UFM, especially the ratio of the first peak flow rate to Qmax , can diagnose DU with high accuracy in men with LUTS.

Development of an artificial intelligence diagnostic system for lower urinary tract dysfunction in men.

OBJECTIVES: To establish an artificial intelligence diagnostic system for lower urinary tract function in men with lower urinary tract symptoms using only uroflowmetry data and to evaluate its usefulness. METHODS: Uroflowmetry data of 256 treatment-naive men with detrusor underactivity, bladder outlet obstruction, or detrusor underactivity + bladder outlet obstruction were used for artificial intelligence learning and validation using neural networks. An optimal artificial intelligence diagnostic model was established using 10-fold stratified cross-validation and data augmentation. Correlations of bladder contractility index and bladder outlet obstruction index values for the artificial intelligence system and pressure flow study values were examined using Spearman's correlation coefficients. Additionally, diagnostic accuracy was compared between the established artificial intelligence system and trained urologists with uroflowmetry data of 25 additional patients by χ2 -tests. Detrusor underactivity was defined as bladder contractility index ≤100 and bladder outlet obstruction index ≤40, bladder outlet obstruction was defined as bladder contractility index >100 and bladder outlet obstruction index >40, and detrusor underactivity + bladder outlet obstruction was defined as bladder contractility index ≤100 and bladder outlet obstruction index >40. RESULTS: The artificial intelligence system's estimated bladder contractility index and bladder outlet obstruction index values showed significant positive correlations with pressure flow study values (bladder contractility index: r = 0.60, P < 0.001; bladder outlet obstruction index: r = 0.46, P < 0.001). The artificial intelligence system's detrusor underactivity diagnosis had a sensitivity and specificity of 79.7% and 88.7%, respectively, and those for bladder outlet obstruction diagnosis were 76.8% and 84.7%, respectively. The artificial intelligence system's average diagnostic accuracy was 84%, which was significantly higher than that of urologists (56%). CONCLUSIONS: Our artificial intelligence diagnostic system developed using the uroflowmetry waveform distinguished between detrusor underactivity and bladder outlet obstruction with high sensitivity and specificity in men with lower urinary tract symptoms.