[1]吴文杰,裴天龙,汪永康,等.基于CT影像组学特征预测肾透明细胞癌分化程度的研究[J].医学信息,2021,34(11):96-100.[doi:10.3969/j.issn.1006-1959.2021.11.026]
　WU Wen-jie,PEI Tian-long,WANG Yong-kang,et al.Study on Predicting Differentiation Degree of Renal Clear Cell Carcinoma Based on CT Imaging Features[J].Medical Information,2021,34(11):96-100.[doi:10.3969/j.issn.1006-1959.2021.11.026]
点击复制

基于CT影像组学特征预测肾透明细胞癌分化程度的研究()
分享到：

医学信息[ISSN:1006-1959/CN:61-1278/R]

卷:
34卷
期数:
2021年11期
页码:
96-100
栏目:
论著
出版日期:
2021-06-01

文章信息/Info

Title:
Study on Predicting Differentiation Degree of Renal Clear Cell Carcinoma Based on CT Imaging Features
文章编号:
1006-1959（2021）11-0096-05
作者:
吴文杰; 裴天龙; 汪永康; 等
（安徽医科大学第二附属医院放射科，安徽 合肥 230601）
Author(s):
WU Wen-jie; PEI Tian-long; WANG Yong-kang; et al.
(Department of Radiology,the Second Affiliated Hospital of Anhui Medical University,Hefei 230601,Anhui,China)
关键词:
肾透明细胞癌; 计算机断层成像; 影像组学
Keywords:
Renal clear cell carcinoma; Computed tomography; Imagingomics
分类号:
R737.11
DOI:
10.3969/j.issn.1006-1959.2021.11.026
文献标志码:
A
摘要:
目的 通过对肾透明细胞癌患者的影像组学信息的提取和分析，构建术前预测模型，以期更好的指导临床进行治疗和预测预后。方法 选取2018年12月~2020年12月安徽医科大学第二附属医院收治的102例肾透明细胞癌患者作为研究对象，根据Fuhrman核分级系统分为分为高分化组（Ⅰ~Ⅱ级）及低分化组（Ⅲ~Ⅳ级），各51例；另将这些患者随机按照7∶3的比例分入训练组72例和验证组30例，均进行腹部CT平扫+三期增强图像，利用mRMR去除冗余和不相关特征后，应用套索方法最终选取出最具预测意义的特征，并采用ROC曲线和AUC建立影像组学模型并进行验证，最终评估模型的诊断效能。结果 选取共10个最有意义的特征，其中7个来自动脉期，1个来自门脉期，2个来自静脉期，没有一个来自延迟期。高分化组及低分化组组间分类结果比较，差异有统计学意义（P＜0.05）。在高分化组和低分化组之间建立评估模型，模型ROC曲线分析显示，训练组AUC=0.85（95%CI：0.75~0.92），灵敏度和特异度分别为0.79和1.00，阳性预测率和阴性预测率分别为1.00和0.65；验证组AUC=0.90（95%CI：0.73~0.98），灵敏度和特异度分别为0.90和0.89，阳性预测率和阴性预测率分别为0.95和0.08。建立肾透明细胞癌预测模型决策曲线分析显示，本研究影像组学模型在0~0.7的较大阈值范围内具有很好的临床应用价值。结论 基于CT的影像组学模型对术前预测肾透明细胞癌分化程度有着较好的效果，可以对临床工作起到一定的指导作用。
Abstract:
Objective To construct a preoperative prediction model by extracting and analyzing the imaging omics information of patients with clear cell renal cell carcinoma, in order to better guide clinical treatment and predict prognosis.Methods From December 2018 to December 2020, 102 patients with renal clear cell carcinoma admitted to the Second Affiliated Hospital of Anhui Medical University were selected as the research objects.According to the Fuhrman nuclear grading system, they were divided into well-differentiated group (grade Ⅰ-Ⅱ) and poorly differentiated group (grade Ⅲ-Ⅳ), each with 51 cases;In addition, these patients were randomly divided into 72 cases in the training group and 30 cases in the verification group according to the ratio of 7:3, and they were all performed abdominal CT plain scan + three-phase enhanced image.After using mRMR to remove redundant and irrelevant features, the lasso method is used to finally select the most predictive features, and the ROC curve and AUC are used to establish and verify the imaging omics model, and finally evaluate the diagnostic efficacy of the model.Results A total of 10 most significant features were selected, of which 7 were from the arterial phase, 1 from the portal phase, 2 from the venous phase, and none from the delayed phase.The comparison of the classification results between the well-differentiated group and the poorly-differentiated group was statistically significant (P<0.05).An evaluation model was established between the well-differentiated group and the poorly-differentiated group. The ROC curve analysis of the model showed that the training group had AUC=0.85 (95%CI: 0.75-0.92), and the sensitivity and specificity were 0.79 and 1.00, respectively.The positive prediction rate and negative prediction rate were 1.00 and 0.65 respectively;In the validation group, AUC=0.90 (95%CI: 0.73-0.98), the sensitivity and specificity were 0.90 and 0.89, and the positive prediction rate and negative prediction rate were 0.95 and 0.08, respectively.The decision curve analysis of the establishment of a renal clear cell carcinoma prediction model showed that the imaging omics model of this study had a good clinical application value within a larger threshold range of 0-0.7.Conclusion CT-based imaging omics model has a good effect on predicting the differentiation degree of clear cell renal cell carcinoma before operation, and can play a certain guiding role in clinical work.

参考文献/References:

[1]Thompson RH,Leibovich BC,Lohse CM,et al.Dynamic Outcome Prediction in Patients With Clear Cell Renal Cell Carcinoma Treated With Radical Nephrectomy: The D-SSIGN Score[J].J Urol,2007,177(2):477-480. [2]Hsieh JJ,Purdue MP,Signoretti S,et al.Renal cell carcinoma[J].Nat Rev Dis Prim,2017(3):1-19. [3]杨熠,钱旭升,周志勇,等.基于CT影像组学特征的肾肿瘤组织学亚型分类[J].北京生物医学工程,2020,39(1):15-20. [4]Lin J,Yu M,Xu X,et al.Identification of biomarkers related to CD8+ T cell infiltration with gene co-expression network in clear cell renal cell carcinoma[J].Aging (Albany NY),2020,12(4):3694-3712. [5]Rouprêt M,Babjuk M,Compérat E,et al.European Association of Urology Guidelines on Upper Urinary Tract Urothelial Carcinoma: 2017 Update[J].Eur Urol,2018,73(1):111-122. [6]Vogel MN,Vatlach M,Weissgerber P,et al.HRCT-features of Pneumocystis jiroveci pneumonia and their evolution before and after treatment in non-HIV immunocompromised patients[J].Eur J Radiol,2012,81(6):1315-1320. [7]胡高杰,樊炳慧,刘群,等.超声造影在肾透明细胞癌不同病理分期中的特征表现及其临床意义[J].内蒙古医科大学学报,2019,41(S1):145-148. [8]Kumar V,Gu Y,Basu S,et al.Radiomics: The process and the challenges[J].Magn Reson Imaging,2012,30(9):1234-1248. [9]Ursprung S,Beer L,Bruining A,et al.Radiomics of computed tomography and magnetic resonance imaging in renal cell carcinoma—a systematic review and meta-analysis[J].Eur Radiol,2020,30(6):3558-3566. [10]Raman SP,Chen Y,Schroeder JL,et al.CT texture analysis of renal masses: Pilot study using random forest classification for prediction of pathology[J].Acad Radiol,2014,21(12):1587-1596. [11]Deng Y,Soule E,Samuel A,et al.CT texture analysis in the differentiation of major renal cell carcinoma subtypes and correlation with Fuhrman grade[J].Eur Radiol,2019,29(12):6922-6929. [12]颜蕾,杨光杰,聂佩,等.基于CT影像组学模型鉴别肾乏脂肪血管平滑肌脂肪瘤与均质肾透明细胞癌[J].中国医学影像技术,2020,36(5):98-103. [13]王平,裴旭,殷小平,等.基于增强CT影像组学模型鉴别肾透明细胞癌与非透明细胞癌[J].中国医学影像技术,2019,35(11):1689-1692. [14]Shu J,Tang Y,Cui J,et al.Clear cell renal cell carcinoma: CT-based radiomics features for the prediction of Fuhrman grade[J].Eur J Radiol,2018(109):8-12. [15]韩冬,贺太平,吴宏培,等.基于CT影像组学构建肾透明细胞癌WHO/ISUP分级的预测模型[J].中华泌尿外科杂志,2019,40(12):889-894. [16]Lambin P,Leijenaar RTH,Deist TM,et al.Radiomics: The bridge between medical imaging and personalized medicine[J].Nat Rev Clin Oncol,2017,14(12):749-762. [17]鲍远照,程琦,严立,等.基于增强CT影像组学特征建立条件推理树模型对肾癌亚型的鉴别诊断[J].中国医学影像学杂志,2020,28(7):520-523. [18]石博文,叶靖,段绍峰,等.T2WI序列纹理分析联合机器学习的影像组学术前预测肾透明细胞癌的病理分级[J].中国医学影像学杂志,2020,28(8):75-78. [19]Ingels A,Leguerney I,Cournède PH,et al.Ultrasound Molecular Imaging of Renal Cell Carcinoma: VEGFR targeted therapy monitored with VEGFR1 and FSHR targeted microbubbles[J].Sci Rep,2020,10(1):7308. [20]Rojas JD,Lin F,Chiang YC,et al.Ultrasound Molecular Imaging of VEGFR-2 in Clear-Cell Renal Cell Carcinoma Tracks Disease Response to Antiangiogenic and Notch-Inhibition Therapy[J].Theranostics,2018,8(1):141-155.

相似文献/References:

[1]桂慧慧,刘 霞.基于多数据库分析MYH10在肾透明细胞癌中的表达与意义[J].医学信息,2022,35(10):20.[doi:10.3969/j.issn.1006-1959.2022.10.004]
　GUI Hui-hui,LIU Xia.Expression and Significance of MYH10 in Renal Clear Cell Carcinoma Based on Multi-database Analysis[J].Medical Information,2022,35(11):20.[doi:10.3969/j.issn.1006-1959.2022.10.004]
[2]毛 伟,张 琳,刘清钊.肾透明细胞癌细胞焦亡相关基因预后模型的建立与应用[J].医学信息,2022,35(14):1.[doi:10.3969/j.issn.1006-1959.2022.14.001]
　MAO Wei,ZHANG Lin,LIU Qing-zhao.Constructionand Application of Pyroptosis-related Genes Prognosis Model in Clear Cell Renal Cell Carcinoma[J].Medical Information,2022,35(11):1.[doi:10.3969/j.issn.1006-1959.2022.14.001]
[3]李 松,李瑞杰,赵小磊.CDKN2A基因突变与肾细胞癌药物敏感性和预后的关系[J].医学信息,2022,35(16):1.[doi:10.3969/j.issn.1006-1959.2022.16.001]
　LI Song,LI Rui-jie,ZHAO Xiao-lei.Relationship Between CDKN2A Gene Mutation and Drug Sensitivity and Prognosis of Renal Cell Carcinoma[J].Medical Information,2022,35(11):1.[doi:10.3969/j.issn.1006-1959.2022.16.001]
[4]李前进,拜合提亚·阿扎提,王文光,等.ST6GalⅠ在肾透明细胞癌中表达及其与病理特征的关系[J].医学信息,2021,34(06):87.[doi:10.3969/j.issn.1006-1959.2021.06.022]
　LI Qian-jin,Baihetia Azati,WANG Wen-guang,et al.The Expression of ST6GalⅠ in Renal Clear Cell Carcinoma and Its Relationship with Pathological Features[J].Medical Information,2021,34(11):87.[doi:10.3969/j.issn.1006-1959.2021.06.022]
[5]单 丽,朱晓力,向程程,等.基于NUF2mRNA、HAMP mRNA、分期、病理分级及年龄的预后评估模型在肾透明细胞癌预后判断中的运用[J].医学信息,2023,36(09):42.[doi:10.3969/j.issn.1006-1959.2023.09.007]
　SHAN Li,ZHU Xiao-li,XIANG Cheng-cheng,et al.The Application of Prognostic Evaluation Model Based on NUF2mRNA,HAMP mRNA,Stage,Pathological Grade and Age in the Prognosis of Kidney Renal Clear Cell Carcinoma[J].Medical Information,2023,36(11):42.[doi:10.3969/j.issn.1006-1959.2023.09.007]

更新日期/Last Update: 1900-01-01