CT平扫影像组学模型在术前预测肾透明细胞癌WHO/ISUP分级的临床价值  

Clinical value of unenhanced CT radiomic model in predicting WHO/ISUP grade of clear cell renal cell carcinoma

作　　者：刘增建 杨帆[1] 张滨[1] 徐井旭 黄陈翠 李万兰 唐美荣 Liu Zengjian;Yang Fan;Zhang Bin(Imaging Department,Peking University Shougang Hospital,Beijing 100144)

机构地区：[1]北京大学首钢医院医学影像科,北京100144 [2]北京大学首钢医院病理科,北京100144

出　　处：《中国现代医药杂志》2022年第7期57-61,共5页Modern Medicine Journal of China

摘　　要：目的探讨术前基于CT平扫影像组学模型预测肾透明细胞癌(Clear cell renal cell carcinoma,ccRCC)世界卫生组织/国际泌尿病理学会(WHO/ISUP)分级中低级别(Ⅰ~Ⅱ级)与高级别(Ⅲ~Ⅳ级)的价值。方法回顾性分析经手术病理证实的201例ccRCC患者共203枚病灶的CT平扫数据(低级别组147枚,高级别组56枚),用图像分割软件获取3D肿瘤感兴趣区(3D-ROI),从3D-ROI中提取5种特征。基于上述特征建立逻辑回归(LR)模型。结果LR模型训练集预测高级别ccRCC的准确度为82.35%、精确度为63.51%,最佳点的敏感性和特异性分别为83.93%和81.76%,AUC为0.893(95%CI:0.8479~0.9381);对应的测试集准确度为79.90%、精确度为60.27%,最佳点的敏感性和特异性分别为78.57%和80.41%,AUC为0.864(95%CI:0.8106~0.9174)。结论基于CT平扫影像组学模型可以对ccRCC WHO/ISUP分级进行术前预测,可为患者的治疗及预后提供参考依据。Objective To investigate the value of unenhanced CT radiomic model in predicting low-grade(WHO/ISUPⅠ~Ⅱ)and high-grade(WHO/ISUPⅢ~Ⅳ)of clear cell renal cell carcinoma(ccRCC).Methods A retrospective analysis was performed on unenhanced CT image features of 203 lesions in 201 patients with ccRCC from Jan 2012 to Dec 2020,all of which were confirmed by surgical pathology(147 lesions in the low-grade group and 56 lesions in the high-grade group).The 3D-ROI was obtained by image segmentation software.LR model was established based on the above characteristics.Results In the training cohort,the accuracy and precision of highlevel ccRCC was 82.35%and 63.51%,the sensitivity and specificity of the optimal point were 83.93%and 81.76%,and the AUC was 0.893(95%CI:0.8479~0.9381).In the test cohort,the accuracy was 79.90%,the precision was 60.27%,the sensitivity and specificity of the optimal point were 78.57%and 80.41%,and the AUC was 0.864(95%CI:0.8106~0.9174).Conclusion The radiomics prediction model based on unenhanced CT can facilitate the preoperative discrimination of the grade of ccRCC.

关 键 词：肾透明细胞癌 体层摄影术 X线计算机 病理分级 影像组学 

分 类 号：R737.11[医药卫生—肿瘤]