Abstract
BACKGROUND: Current prognostic models have limited predictive abilities for the growing number of localized (stage I-III) ccRCCs. It is, therefore, crucial to explore novel preoperative recurrence prediction models to accurately stratify patients and optimize clinical decisions. The purpose of this study was to develop and externally validate a computed tomography (CT)-based deep learning (DL) model for presurgical disease-free survival (DFS) prediction. METHODS: Patients with localized ccRCC were retrospectively enrolled from six independent medical centers. Three-dimensional (3D) tumor regions from CT images were utilized as input to architect a ResNet 50 model, which outputted DL computed risk score (DLCR) of each patient for DFS prediction later. The predictive performance of DLCR was assessed and compared to the radiomics model (Rad-Score), the clinical model the authors built and two existing prognostic models (UISS and Leibovich). The complementary value of DLCR to the UISS, Leibovich, as well as Rad-Score were evaluated by stratified analysis. RESULTS: Seven hundred seven patients with localized ccRCC were finally enrolled for models' training and validating. The DLCR the authors established can perfectly stratify patients into low-risks, intermediate-risks, and high-risks, and outperformed the Rad-Score, clinical model, UISS and Leibovich score in DFS prediction, with a C-index of 0.754 (0.689-0.821) in the external testing set. Furthermore, the DLCR presented excellent risk stratification capacity in subgroups defined by almost all clinic-pathological features. Moreover, patients classified as low-risk by the UISS/Leibovich score/Rad-Score but as intermediate - or high-risk by DLCR were significantly more likely to experience ccRCC recurrence than those stratified as intermediate- or high-risk by UISS/Leibovich score/Rad-Score but as low-risk by DLCR (all Log-rank P- values<0.05). CONCLUSIONS: Our DL model, derived from preoperative CT, is superior to radiomics and current models in precisely DFS predicting of localized ccRCC, and can provide complementary values to them, which may assist more informed clinical decisions and adjuvant therapies adoptions.