Association of AI-derived abdominal organ volumetry with postoperative outcomes in clear cell renal cell carcinoma: a multicentre study

This is the authors' abstract. We don't add key points for this paper.

BACKGROUND: CT-derived body composition parameters are associated with clinical outcomes in clear cell renal cell carcinoma (ccRCC), but the prognostic value of abdominal solid organ volumes remains unclear. METHODS: In this multicentre study, 1,720 patients with ccRCC who underwent nephrectomy across four centres and 3,052 healthy controls were included. A deep learning algorithm was used to automatically quantify abdominal organ volumes. Organ volume indices were calculated by normalizing volumes to body surface area. Associations between abdominal organ volumes and recurrence-free survival (RFS) and overall survival (OS) were evaluated using centre-stratified Cox regression models. Multivariable models were adjusted for age, gender, tumour size, laterality, surgical approach, pT stage, pN stage, International Society of Urological Pathology grade and tumor necrosis. RESULTS: adj = 0.035) were independently associated with worse OS. No parameter was associated with RFS after multiple-testing correction. CONCLUSIONS: Higher liver and right adrenal gland volumes were associated with worse OS in ccRCC. These findings warrant external validation and further mechanistic investigation.