Department of Medical Imaging, The Ottawa Hospital, 1053 Carling Ave, Rm C159, Ottawa, ON K1Y 4E9, Canada.
Department of Pathology, The Ottawa Hospital, Ottawa, ON, Canada.
AJR Am J Roentgenol. 2022 Nov;219(5):814-823. doi: 10.2214/AJR.22.27971. Epub 2022 Jun 29.
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. The purpose of our study was to develop and evaluate a CT-based algorithm for diagnosing ccRCC among small (≤ 4 cm) solid renal masses. 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. 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, = .02; reader 2: 0.75 ± 0.29 vs 0.59 ± 0.25, = .02). The heterogeneity score was higher for ccRCC than other diagnoses (reader 1: 4.0 ± 1.1 vs 1.5 ± 1.6, < .001; reader 2: 4.4 ± 0.9 vs 3.3 ± 1.5, < .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 κ) 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. 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. The CT algorithm, if validated, may represent a useful clinical tool for diagnosing ccRCC.
MRI 透明细胞可能性评分可预测肾脏肿块为透明细胞肾细胞癌（ccRCC）的可能性。尚未建立基于 CT 的算法。本研究的目的是开发和评估一种基于 CT 的算法，用于诊断≤ 4cm 的小（≤ 4cm）实性肾脏肿块中的 ccRCC。这项回顾性研究纳入了 148 名患者（73 名男性，75 名女性；平均年龄 58 ± 12[SD]岁），这些患者在 2016 年 1 月至 2019 年 12 月期间接受了肾肿块 CT（未增强、皮质髓质和肾图期）检查，然后进行了肾肿块切除术。两位放射科医生独立评估 CT 检查并记录了钙化、各期肿块衰减值、肿块与皮质髓质衰减比值和异质性评分（5 分李克特量表评估，在皮质髓质期评估）。多变量逻辑回归分析确定与 ccRCC 相关的特征，然后使用这些特征创建用于诊断 ccRCC 的五等级 CT 评分。肿块包括 53%（78/148）ccRCC 和 47%（70/148）其他组织学诊断。ccRCC 的肿块与皮质髓质衰减比值高于其他诊断（读者 1：0.84 ± 0.68 vs 0.68 ± 0.65，=.02；读者 2：0.75 ± 0.29 vs 0.59 ± 0.25，=.02）。ccRCC 的异质性评分高于其他诊断（读者 1：4.0 ± 1.1 vs 1.5 ± 1.6，<.001；读者 2：4.4 ± 0.9 vs 3.3 ± 1.5，<.001）。其他特征无差异。包括肿块与皮质髓质衰减比值和异质性评分的五级诊断算法观察者间一致性为 0.71（加权 κ），用于诊断 ccRCC 的 AUC 为 0.75（95%CI，0.68-0.82），读者 1 为 0.72（95%CI，0.66-0.82），读者 2为 0.72（95%CI，0.66-0.82）。CT 评分≥ 4 时，读者 1 的敏感性、特异性和阳性预测值分别为 71%（95%CI，59-80%）、79%（95%CI，67-87%）和 79%（95%CI，67-87%），读者 2 的敏感性、特异性和阳性预测值分别为 42%（95%CI，31-54%）、81%（95%CI，70-90%）和 72%（95%CI，56-84%）。CT 评分≤ 2 时，读者 1 的阴性预测值为 85%（95%CI，69-95%），读者 2 的阴性预测值为 88%（95%CI，69-97%）。包括肿块与皮质髓质衰减比值和异质性评分的五等级肾 CT 算法，具有良好的观察者间一致性、中等 AUC 和阳性预测值以及高阴性预测值，用于诊断 ccRCC。如果经过验证，该 CT 算法可能成为诊断 ccRCC 的有用临床工具。
