Search

Objective: To automate the generation of three validated nephrometry scoring systems on preoperative computerised tomography (CT) scans by developing artificial intelligence (AI)-based image processing methods. Subsequently, we aimed to evaluate the ability of these scores to predict meaningful pathological and perioperative outcomes., Patients and Methods: A total of 300 patients with preoperative CT with early arterial contrast phase were identified from a cohort of 544 consecutive patients undergoing surgical extirpation for suspected renal cancer. A deep neural network approach was used to automatically segment kidneys and tumours, and then geometric algorithms were used to measure the components of the concordance index (C-Index), Preoperative Aspects and Dimensions Used for an Anatomical classification of renal tumours (PADUA), and tumour contact surface area (CSA) nephrometry scores. Human scores were independently calculated by medical personnel blinded to the AI scores. AI and human score agreement was assessed using linear regression and predictive abilities for meaningful outcomes were assessed using logistic regression and receiver operating characteristic curve analyses., Results: The median (interquartile range) age was 60 (51-68) years, and 40% were female. The median tumour size was 4.2 cm and 91.3% had malignant tumours. In all, 27% of the tumours were high stage, 37% high grade, and 63% of the patients underwent partial nephrectomy. There was significant agreement between human and AI scores on linear regression analyses (R ranged from 0.574 to 0.828, all P < 0.001). The AI-generated scores were equivalent or superior to human-generated scores for all examined outcomes including high-grade histology, high-stage tumour, indolent tumour, pathological tumour necrosis, and radical nephrectomy (vs partial nephrectomy) surgical approach., Conclusions: Fully automated AI-generated C-Index, PADUA, and tumour CSA nephrometry scores are similar to human-generated scores and predict a wide variety of meaningful outcomes. Once validated, our results suggest that AI-generated nephrometry scores could be delivered automatically from a preoperative CT scan to a clinician and patient at the point of care to aid in decision making., (© 2024 BJU International.)

Objectives: To evaluate predictors of long-term survival for patients with chronic kidney disease primarily due to surgery (CKD-S). Patients with CKD-S have generally good survival that approximates patients who do not have CKD even after renal cancer surgery (RCS), yet there may be heterogeneity within this cohort., Patients and Methods: From 1997 to 2008, 4 246 patients underwent RCS at our centre. The median (interquartile range [IQR]) follow-up was 9.4 (7.3-11.0) years. New baseline glomerular filtration rate (GFR) was defined as highest GFR between nadir and 6 weeks after RCS. We retrospectively evaluated three cohorts: no-CKD (new baseline GFR of ≥60 mL/min/1.73 m 2 ); CKD-S (new baseline GFR of <60 mL/min/1.73 m 2 but preoperative GFR of ≥60 mL/min/1.73 m 2 ); and CKD due to medical aetiologies who then require RCS (CKD-M/S, preoperative and new baseline GFR both <60 mL/min/1.73 m 2 ). Analysis focused primarily on non-renal cancer-related survival (NRCRS) for the CKD-S cohort. Kaplan-Meier analysis assessed the longitudinal impact of new baseline GFR (45-60 mL/min/1.73 m 2 vs <45 mL/min/1.73 m 2 ) and Cox regression evaluated relative impact of preoperative GFR, new baseline GFR, and relevant demographics/comorbidities., Results: Of the 4 246 patients who underwent RCS, 931 had CKD-S and 1 113 had CKD-M/S, whilst 2 202 had no-CKD even after RCS. Partial/radical nephrectomy (PN/RN) was performed in 54%/46% of the patients, respectively. For CKD-S, 641 patients had a new baseline GFR of 45-60 mL/min/1.73 m 2 and 290 had a new baseline GFR of <45 mL/min/1.73 m 2 . Kaplan-Meier analysis showed significantly reduced NRCRS for patients with CKD-S with a GFR of <45 mL/min/1.73 m 2 compared to those with no-CKD or CKD-S with a GFR of 45-60 mL/min/1.73 m 2 (both P ≤ 0.004), and competing risk analysis confirmed this (P < 0.001). Age, gender, heart disease, and new baseline GFR were all associated independently with NRCRS for patients with CKD-S (all P ≤ 0.02)., Conclusion: Our data suggest that CKD-S is heterogeneous, and patients with a reduced new baseline GFR have compromised survival, particularly if <45 mL/min/1.73 m 2 . Our findings may have implications regarding choice of PN/RN in patients at risk of developing CKD-S., (© 2017 The Authors BJU International © 2017 BJU International Published by John Wiley & Sons Ltd.)