A deep learning algorithm based on contrast-enhanced multiphase CT demonstrated good performance for characterizing small (≤3 cm) renal masses as benign lesions.

The radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry score could be used to predict surgical outcomes and renal tumour aggressiveness. We aimed to analyse its associations with survival outcomes. We included 1368 patients with sporadic, unilateral and non-metastatic renal tumours who received curative nephrectomy in Zhongshan Hospital from January 2009 to September 2019. Radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry scores were assigned by three urologists based on preoperative CT/MRI scans. Correlations between parameters or sum of radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry scores, overall survival and recurrence-free survival were analysed by Kaplan–Meier analyses and the multivariate Cox regression model. We further compared survival outcomes between patients who received partial nephrectomy and patients who received radical nephrectomy. We observed statistically significant associations between all components of radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry scores and oncologic outcomes, including R (radius) (overall survival, P < 0.001; recurrence-free survival , P < 0.001), E (exophytic/endophytic) (overall survival, P = 0.003; recurrence-free survival, P < 0.001), N (nearness) (overall survival, P = 0.063; recurrence-free survival, P < 0.001), A (anterior/posterior) (overall survival, P < 0.001; recurrence-free survival, P = 0.005), L (location) (overall survival, P = 0.008; recurrence-free survival, P < 0.001) and suffix ‘h’ (overall survival, P = 0.237; recurrence-free survival, P = 0.034). Kaplan–Meier curves of overall survival and recurrence-free survival rates were significantly different when stratified by radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry score complexity group (overall survival, P < 0.001; recurrence-free survival, P < 0.001). After adjusting for tumour stage and grade, radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry score as continuous variables was an adverse independent risk factor for survival outcomes [P = 0.027, hazard ratio (95% confidence interval) = 1.151 (1.016–1.303)] and recurrence-free survival [P < 0.001, hazard ratio (95% confidence interval) = 1.299 (1.125–1.501)]. For tumours with radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry scores of 4 and 5, partial nephrectomy showed a survival benefit than radical nephrectomy. Both components and complexity groups of the radius-exophytic/endophytic-nearness-anterior/posterior-location nephrometry score are associated with survival outcomes in renal tumour patients.