Development of a Multiparametric Renal CT Algorithm for Diagnosis of Clear Cell Renal Cell Carcinoma Among Small (≤ 4 cm) Solid Renal Masses

BACKGROUND. The MRI clear cell likelihood score predicts the likelihood that a renal mass is clear cell renal cell carcinoma (ccRCC). A CT-based algorithm has not yet been established. OBJECTIVE. The purpose of our study was to develop and evaluate a CT-based algorithm for diagnosing ccRCC among small (<= 4 cm) solid renal masses. METHODS. This retrospective study included 148 patients (73 men, 75 women; mean age, 58 +/- 12 [SD] years) with 148 small (<= 4 cm) solid (> 25% enhancing tissue) renal masses that underwent renal mass CT (unenhanced, corticomedullary, and nephrographic phases) before resection between January 2016 and December 2019. Two radiologists independently evaluated CT examinations and recorded calcification, mass attenuation in all phases, mass-to-cortex corticomedullary attenuation ratio, and heterogeneity score (score on a 5-point Likert scale, assessed in corticomedullary phase). Features associated with ccRCC were identified by multivariable logistic regression analysis and then used to create a five-tiered CT score for diagnosing ccRCC. RESULTS. The masses comprised 53% (78/148) ccRCC and 47% (70/148) other histologic diagnoses. The mass-to-cortex corticomedullary attenuation ratio was higher for ccRCC than for other diagnoses (reader 1: 0.84 +/- 0.68 vs 0.68 +/- 0.65, p =.02; reader 2: 0.75 +/- 0.29 vs 0.59 +/- 0.25, p =.02). The heterogeneity score was higher for ccRCC than other diagnoses (reader 1: 4.0 +/- 1.1 vs 1.5 +/- 1.6, p <.001; reader 2: 4.4 +/- 0.9 vs 3.3 +/- 1.5, p <.001). Other features showed no difference. A five-tiered diagnostic algorithm including the mass-to- cortex corticomedullary attenuation ratio and heterogeneity score had interobserver agreement of 0.71 (weighted.) and achieved an AUC for diagnosing ccRCC of 0.75 (95% CI, 0.68-0.82) for reader 1 and 0.72 (95% CI, 0.66-0.82) for reader 2. A CT score of 4 or greater achieved sensitivity, specificity, and PPV of 71% (95% CI, 59-80%), 79% (95% CI, 67-87%), and 79% (95% CI, 67-87%) for reader 1 and 42% (95% CI, 31-54%), 81% (95% CI, 70-90%), and 72% (95% CI, 56- 84%) for reader 2. A CT score of 2 or less had NPV of 85% (95% CI, 69-95%) for reader 1 and 88% (95% CI, 69-97%) for reader 2. CONCLUSION. A five-tiered renal CT algorithm, including the mass-to-cortex corticomedullary attenuation ratio and heterogeneity score, had substantial interobserver agreement, moderate AUC and PPV, and high NPV for diagnosing ccRCC. CLINICAL IMPACT. The CT algorithm, if validated, may represent a useful clinical tool for diagnosing ccRCC.

Automated summary

This study developed a CT-based algorithm for diagnosing ccRCC among small solid renal masses. By evaluating the mass-to-cortex corticomedullary attenuation ratio and heterogeneity score, the algorithm can accurately diagnose ccRCC.