Development and validation of a CT algorithm based on intratumoral necrosis and tumor morphology to predict the nuclear grade of small (2-4 cm) solid clear cell renal cell carcinoma.

Abstract

Background: Preoperative non-invasive prediction of the World Health Organization/International Society of Urological Pathology (WHO/ISUP) nuclear grade of small clear cell renal cell carcinoma (ccRCC) can aid in decision making for active surveillance. The study aimed to develop and validate a CT algorithm for the prediction of the WHO/ISUP nuclear grade of small (2-4 cm) solid ccRCC.

Methods: A total of 233 patients with 233 ccRCCs (50 high-grade [WHO/ISUP grades 3-4] and 183 low-grade [WHO/ISUP grades 1-2]) in the initial cohort were enrolled in this study. The tumor necrosis (presence of necrosis, proportion of necrosis, and tumor necrosis score [TNS]) and tumor morphology (five grades) were retrospectively evaluated using contrast-enhanced CT. A four-tiered CT score based on TNS and shape irregularity score (SIS) was constructed using logistic regression and receiver operating characteristic (ROC) curve analyses. The effectiveness of the four-tiered CT score was confirmed through an external validation cohort (218 ccRCCs from 218 patients, including 42 high-grade and 176 low-grade).

Results: The TNS and tumor morphologies significantly differed between high-grade and low-grade ccRCCs (both P < 0.001). For diagnosis of high-grade ccRCC, the TNS and SIS achieved the area under the ROC curve (AUC) values of 0.697 and 0.731, respectively. The four-tiered CT score had an interobserver agreement of 0.677 (Cohen kappa), and achieved the AUC values of 0.793 and 0.781 in the initial and validation cohorts, respectively. The CT score of ≥ 3 exhibited a sensitivity of 54.00% and 54.76% in the initial and validation cohorts, respectively, with corresponding specificity of 90.16% and 88.07%, accuracy of 82.40% and 81.65%, positive predictive value of 60.00% and 52.27%, and negative predictive value (NPV) of 87.77% and 89.08%.

Conclusions: The TNS based on the number and size of necrotic foci could help diagnose high-grade ccRCC. The developed CT score algorithm achieved moderate AUC and high NPV for the diagnosis of high-grade ccRCC, which might facilitate active surveillance for ccRCC with a diameter of 2-4 cm.