Magnetic Resonance Imaging Radiomics Analyses for Prediction of High-Grade Histology and Necrosis in Clear Cell Renal Cell Carcinoma: Preliminary Experience.
Magnetic Resonance Imaging Radiomics Analyses for Prediction of High-Grade Histology and Necrosis in Clear Cell Renal Cell Carcinoma: Preliminary Experience.
复制标题
磁共振成像放射组学分析预测肾透明细胞癌高级别组织学和坏死：初步经验。
DOI：
10.1016/j.clgc.2020.05.011
复制
发表时间：
2021-03
影响因子：
3.2
通讯作者：
Pedrosa I
中科院分区：
文献类型：
--
作者：
Dwivedi DK;Xi Y;Kapur P;Madhuranthakam AJ;Lewis MA;Udayakumar D;Rasmussen R;Yuan Q;Bagrodia A;Margulis V;Fulkerson M;Brugarolas J;Cadeddu JA;Pedrosa I
经皮肾肿块活检可以准确诊断透明细胞肾细胞癌 (ccRCC)，但其确定较大异质肿瘤核分级的可靠性有限。评估磁共振成像 (MRI) 放射组学分析预测 ccRCC 高级别 (HG) 组织学的能力。 2012年8月至2017年8月期间，70名患有肾脏肿块的患者在手术前接受了3T MRI检查。手动肿瘤分割后，在 T2 加权 (T2W) 和动态对比增强 (DCE) MRI 上计算肿瘤长度、一阶统计数据和 Haralick 纹理特征。应用变量聚类算法后，通过受试者工作特征（ROC）曲线对肿瘤长度、清除和所有聚类特征进行单变量评估。构建了三个逻辑回归模型来评估 HG ccRCC 的可预测性并进行交叉验证。在单变量分析中，诊断 HG ccRCC 的长度、DCE 纹理簇 1 和簇 3 的曲线下面积 (AUC) 分别为 0.7（95% CI，0.58-0.82，错误发现率 (FDR) p 值 = 0.008）、0.72（95% 置信区间 (CI)，0.59-0.84，FDR p 值 = 0.004）和分别为 0.75（95% CI，0.63-0.87，FDR p 值 = 0.0009）。在多变量分析中，诊断 HG ccRCC 的模型 1（仅肿瘤长度）、模型 2（长度 + DCE 簇 3 和 4）和模型 3（DCE 簇 1 和 3）的 AUC 分别为 0.67（95% CI，0.54-0.79）、0.82（95% CI，0.71-0.92）和 0.81（95% CI， 0.70-0.91），分别。在我们的队列中，对于 ccRCC 的高级组织学预测，MRI 图像的放射组学分析优于肿瘤大小。放射组学分析包括磁共振成像 (MRI) 的直方图数据和 Haralick 纹理特征，与肿瘤大小相比，为确定透明细胞肾细胞癌 (ccRCC) 患者的肿瘤分级提供了合理且优越的诊断性能。基于 MRI 的放射组学可能在具有异质性肿瘤的 ccRCC 患者的治疗决策中发挥经皮肾活检的辅助作用。
Percutaneous renal mass biopsies can accurately diagnose clear cell renal cell carcinoma (ccRCC), however their reliability to determine nuclear grade in larger, heterogeneous tumors is limited. To assess the ability of radiomics analyses of magnetic resonance imaging (MRI) to predict high grade (HG) histology in ccRCC. 70 patients with a renal mass underwent 3T MRI before surgery between 8/2012 and 8/2017. Tumor length, first order statistics, and Haralick texture features were calculated on T2-weighted (T2W) and dynamic contrast enhanced (DCE) MRI after manual tumor segmentation. After variable clustering algorithm was applied, tumor length, wash-out and all cluster features were evaluated univariably by receiver operating characteristic (ROC) curves. Three logistic regression models were constructed to assess predictability of HG ccRCC and cross-validated. At univariate analysis, area under the curve (AUC) of length, DCE texture cluster 1 and cluster 3 for diagnosis of HG ccRCC were 0.7 (95% CI, 0.58-0.82, false discovery rate (FDR) p-value = 0.008), 0.72 (95% confidence interval (CI), 0.59-0.84, FDR p-value = 0.004) and 0.75 (95% CI, 0.63-0.87, FDR p-value = 0.0009), respectively. At multivariable analysis, AUC for model 1 (tumor length only), model 2 (length + DCE clusters 3 and 4), and model 3 (DCE cluster 1 and 3) for diagnosis of HG ccRCC were 0.67 (95% CI, 0.54-0.79), 0.82 (95% CI, 0.71-0.92), and 0.81 (95% CI, 0.70-0.91), respectively. Radiomics analysis of MRI images was superior to tumor size for the prediction of high-grade histology in ccRCC in our cohort. Radiomics analyses including histogram data and Haralick texture features of magnetic resonance imaging (MRI) offer a reasonable and superior diagnostic performance compared to tumor size for the determination of tumor grade in patients with clear cell renal cell carcinoma (ccRCC). MRI-based radiomics may play an adjunct role to percutaneous renal biopsy in management decisions of ccRCC patients with heterogeneous tumors.
登录
查看更多内容
影响因子：
19.7
作者：
Horvat, Natally;Veeraraghavan, Harini;Petkovska, Iva
通讯作者：
Petkovska, Iva
影响因子：
19.7
作者：
Hindman, Nicole;Ngo, Long;Pedrosa, Ivan
通讯作者：
Pedrosa, Ivan
DOI：
10.1073/pnas.1505935112
发表时间：
2015-11-17
影响因子：
11.1
作者：
Fehr, Duc;Veeraraghavan, Harini;Deasy, Joseph O.
通讯作者：
Deasy, Joseph O.
影响因子：
19.7
作者：
Chandarana, Hersh;Rosenkrantz, Andrew B.;Kiraly, Atilla P.
通讯作者：
Kiraly, Atilla P.
影响因子：
1.9
作者：
Kay FU;Pedrosa I
通讯作者：
Pedrosa I