Development and validation of a CT-based nomogram for preoperative prediction of clear cell renal cell carcinoma grades.

影響因子： 4.101PMID：33515086期刊年卷：Eur Radiol 2021 Jan 29;醫學二區 核醫學 Q1 20/129DOI：10.1007/s00330-020-07667-y作者列表: Zheng Z, Chen Z, Xie Y, Zhong Q, Xie W,

OBJECTIVES:Nuclear grades are proved to be one of the most significant prognostic factors for clear cell renal cell carcinoma (ccRCC). Radiomics nomogram is a widely used noninvasive tool that could predict tumor phenotypes. In this study, we performed radiomics analysis to develop and validate a CT-based nomogram for the preoperative prediction of nuclear grades in ccRCC.

METHOD:CT images and clinical data of 258 ccRCC patients were retrieved from the Cancer Imaging Archive (TCIA). Radiomics features were extracted from arterial-phase CT images using 3D Slicer software. LASSO regression model was performed to develop a radiomics signature in the training set (n = 143). A radiomics nomogram was constructed combining radiomics signature and selected clinical predictors. Receiver operating characteristic (ROC) curve and calibration curve were used to determine the performance of the radiomics nomogram in the training and validation set (n = 115). Decision curve analysis was used to assess the clinical usefulness of the CT-based nomogram.

RESULTS:One thousand three hundred sixteen radiomics features were extracted from arterial-phase CT images. A radiomics signature, consisting of 20 features, was developed and showed a favorable performance in discriminating nuclear grades with an area under the curve (AUC) of 0.914 and 0.846 in the training and validation set, respectively. The CT-based nomogram, including the radiomics signature and the CT-determined T stage, achieved good calibration and discrimination in the training set (AUC, 0.929; 95% CI, 0.886-0.972) and validation set (AUC, 0.876; 95% CI, 0.812-0.939). Decision curve analysis demonstrated the clinical usefulness of the CT-based nomogram.

CONCLUSION:The noninvasive CT-based nomogram, including radiomics signature and CT-determined T stage, could improve the accuracy of preoperative grading of ccRCC and provide individualized treatment for ccRCC patients.

KEY POINTS:• Contrast-enhanced CT may help in preoperative grading of ccRCC. • The CT-based nomogram incorporated a radiomics signature and CT-determined T stage could preoperatively predict ccRCC grades. • The CT-based nomogram has the potential to improve individualized treatment and assist clinical decision making of ccRCC patients.

基於CT的腎透明細胞癌術前分級預測標準圖的開發和驗證

目的：核分級是影響腎透明細胞癌(CcRCC)預後的重要因素之一。放射組學諾模圖是一種廣泛使用的可預測腫瘤表型的非侵入性工具。在這項研究中，我們進行了放射組學分析，以開發和驗證一種基於CT的諾模圖，用於術前預測腎細胞癌的核級別。

方法：從腫瘤影像檔案館(TCIA)檢索258例腎細胞癌患者的CT影象和臨床資料。使用3D Slicer軟體從動脈期CT影象中提取放射組學特徵。使用套索迴歸模型在訓練集中建立放射組學特徵(n= 143)。結合放射組學特徵和選定的臨床預測因子，構建放射組學諾模圖。使用受試者操作特徵曲線和校準曲線來確定放射組學諾模圖在訓練和驗證集(n = 115)中的效能。決策曲線分析用於評估基於CT的諾模圖的臨床實用性。

結果：從動脈期CT影象中提取了1,316個放射組學特徵。開發了一個由20個特徵組成的放射組學特徵，在識別核級別方面表現出良好的效能，在訓練和驗證集中的曲線下面積(AUC值)分別為0.914和0.846。基於CT的諾模圖，包括放射組學特徵和CT確定的T分期，在訓練集(AuC，0.929；95%CI，0.886-0.972)和驗證集(AuC，0.876；95%CI，0.812-0.939)上取得了良好的校準和判別效果。決策曲線分析證明了基於CT的諾模圖的臨床應用價值。

結論：包括放射組學徵象和CT確定的T分期在內的無創性CT諾莫圖可以提高腎癌術前分級的準確性，為腎癌患者提供個體化治療。

要點：·CT增強掃描有助於腎細胞癌的術前分級。·結合放射組學特徵和CT確定的T分期的基於CT的諾模圖可以在術前預測ccRCC的分級。·基於CT的諾模圖有可能提高ccRCC患者的個體化治療，並輔助臨床決策。