[1]王元元,张祥林△,吕晓虹.CT图像容积纹理分析在肾透明细胞癌病理分级中的应用研究[J].陕西医学杂志,2020,49(3):304-308,312.
　WANGYuanyuan,ZHANG Xianglin..Application of CT volumetric texture analysis in pathological grade of clear cell renal cell carcinoma[J].,2020,49(3):304-308,312.
点击复制

CT图像容积纹理分析在肾透明细胞癌病理分级中的应用研究
分享到：

《陕西医学杂志》[ISSN:1000-7377/CN:61-1281/TN]

卷:
49
期数:
2020年3期
页码:
304-308,312
栏目:
临床研究
出版日期:
2020-03-05

文章信息/Info

Title:
Application of CT volumetric texture analysis in pathological grade of clear cell renal cell carcinoma
文章编号:
DOI:〖HT5K〗10.3969/j.issn.10007377.2020.03.011
作者:
王元元; 张祥林△; 吕晓虹
锦州医科大学附属第一医院放射科(锦州 121000)
Author(s):
WANGYuanyuan; ZHANG Xianglin.
Department of Radiology,the First Hospital of Jinzhou Medical University(Jinzhou 121000)
关键词:
肾肿瘤;  体层摄影术;  X线计算机;  纹理分析;  肾细胞癌;  病理分级
Keywords:
Kidney neoplasms;  Tomography;  X-ray computed;  Texture analysis;  Renal cell carcinoma;  Pathological grade
分类号:
R445.3
文献标志码:
A
摘要:
目的:探讨CT图像容积纹理分析在肾透明细胞癌(CCRCC)病理分级中的应用价值。方法:回顾性分析经手术病理活检确诊为CCRCC的67例患者(68个病灶)的皮质期及实质期图像,ITK-Snap软件逐层手动勾画ROI,利用A.K.软件提取ROI纹理特征。先后使用三种方法依次对预处理后的数据进行降维:单因素方差分析及秩和检验、Spearman相关性分析、最小绝对收缩及选择算子即Lasso。筛选出的纹理特征在高、低级别CCRCC间的差异进行统计学分析,对其纹理参数绘制ROC曲线,获取其曲线下面积(AUC)、灵敏度、特异度,进行分析。结果:降维后,皮质期、实质期分别筛选出5、8个纹理特征; 经两独立样本Mann-whitney U检验后,皮质期、实质期分别有4、5个纹理参数有统计学意义; 通过ROC曲线进行比较,两个时相参数中均是Maximum 3D Diameter的病理分级评估效能最大,其皮质期、实质期AUC分别为0.879、0.883,分别以80.6536、68.1836为阈值,诊断的灵敏度分别为83.30%、91.70%,特异度分别为86.40%、81.80%; 其余参数AUC均大于0.7,具有中等预测效能。结论:CT图像容积纹理分析可以用于肾透明细胞癌术前病理分级的预测。
Abstract:
Objective:To explore the value of CT volumetric texture analysis in pathological grade of clear cell renal cell carcinoma(CCRCC).Methods:The cortical phase and substantive phase CT images of 67 patients(68 lesions)diagnosed with CCRCC by surgery or pathological biopsy were retrospectively analyzed.The ITK-Snap software was used to manually outline the ROI layer by layer.The A.K.software was used for the ROI texture extraction.Three methods were used to reduce the dimension of the pre-processed data in turn:one-way ANOVA and rank sum test,Spearman correlation analysis,the least absolute shrinkage and selection operator(LASSO).The difference of selected texture features between high-level and low-level CCRCC was analyzed statistically.ROC curves were drawn to obtain the area under the curve(AUC),sensitivity and specificity.Results:5 and 8 texture features were screened out during dimensionality reduction,and 4 and 5 texture features had statistical significances after Mann-whitney U test in cortical phase and substantive phase,respectively.Maximum 3D Diameter was the most effective parameter.Its AUC,sensitivity and specificity was respectively 0.879,83.30%,86.40% in cortical phase and 0.883,91.70%,81.80% in substantive phase.The AUC of other parameters were greater than 0.7,which showed medium prediction efficiency.Conclusion:Volume texture analysis of CT images can be used to predict the preoperative pathological grade of CCRCC.

参考文献/References:

[1] Capitanio U,Montorsi F.Renal cancer[J].Lancet,2016,387(10021):894-906.
[2] Patard JJ,Leray E,Riouxleclercq N,et al.Prognostic value of histologic subtypes in renal cell carcinoma:a multicenter experience[J].J Clin Oncol,2005,23(12):2763-2771.
[3] Lam JS,Klatte T,Breda A.Staging of renal cell carcinoma:current concepts.[J].Indian J Urol,2009,25(4):446-454.
[4] Philippe L,Emmanuel RV,Ralph L,et al.Radiomics:extracting more information from medical images using advanced feature analysis[J].Eur J Cancer,2007,43(8):441-446.
[5] 武 松,潘发明,等.SPSS统计分析大全[M].北京:清华大学出版社,2014:180-181.
[6] Tran T,Jones CL,Williamson SR.Tubulocystici renal cell carcinoma is an entity that is immunohistochemically and genetically distinct from papillay renal cell carcinoma[J].Histopathology,2016,68(6):850-857.
[7] Kim H,Inomoto C,Uchida T.Verification of the international society of urological pathology recommendationsin japanese patients with clear cell renal cell carcinoma[J].Int J Oncol,2018,52(4):1139-1148.
[8] Dagher J,Delahunt B,Rioux-Leclercq N.Clear cell renal cell carcinoma:validation of World Health Organization/International Society of Urological Pathology grading.Histopathology,2017,71(6):918-925.
[9] 刘春梅.肾透明细胞癌病理分级与其超声特征的相关性评价[J].实用医技杂志,2019,26(4):436-438.
[10] 程蛰承,李志坚,徐 骥,等.肾透明细胞癌64排多层螺旋CT直接征象与病理学分级的对比研究[J].肿瘤影像学,2019,28(2):117-122.
[11] Alobaidli S,Mcquaid S,South C,et al.The role of texture analysis in imaging as an outcome predictor and potential tool in radiotherapy treatment planning[J].Br J Radiol,2014,87(1042):20140369.
[12] Larue RT,Defraene G,De RD,et al.Quantitative radiomics studies for tissue characterization:a review of technology and methodological procedures[J].Br J Radiol,2017,90(1070):20160665.
[13] Avanzo M,Stancanello J,Einaqa I.Beyond imaging:The promise of radiomics[J].Phys Med,2017,38:122-139.
[14] Schieda N,Thornhill RE,Al-Subhi M,et al.Diagnosis of sarcomatoid renal cell carcinoma with CT:Evaluation by qualitative imaging features and texture analysis[J].AJR Am J Roentgenol,2015,204(5):1013-1023.
[15] Yan L,Liu Z,Wang G,et al.Angiomyolipoma with minimal fat:differentiation from clear cell renal cell carcinoma and papillary renal cell carcinoma by texture analysis on CT images[J].Acad Radiol,2015,22(9):1115-1121.
[16] 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.
[17] Georgiadis P,Cavouras D,Kalatzis I,et al.Enhancing the discrimination accuracy between metastases,gliomas and meningiomas on brain MRI by volumetric textural features and ensemble pattern recognition methods[J].Magn Reson Imaging,2009,27(1):120-130.
[18] El-Baz A,Casanova M,Gimel Farb G,et al.Dyslexia diagnostics by 3D texture analysis of cerebral white matter gyrifications[C].International Conference on Medical Image Computing & Computer-assisted Intervention:Springer-Verlag,2007.
[19] Bektas CT,Kocak B,Yardimci AH,et al.Clear cell renal cell carcinoma:machine learning -based quantitative computed tomography texture analysis for prediction of fuhrman nuclear grade[J].Eur Radiol,2019,29(3):1153-1163.
[20] Lubner MG,Stabo N,Abel EJ,et al.CT textural analysis of large primary renal cell carcinomas:pretreatment tumor heterogeneity correlates with histologic findings and clinical outcomes[J].Am J Roentgenol,2016,207(1):96-105.
[21] Kierans AS,Rusinek H,Lee A,et al.Textural diferences inapparent difusion coefcient between low- and high-stage clear cell renal cell carcinoma[J].AJR Am J Roentgenol,2014,203(6):637-644.
[22] 李淑兰,张学兰,周祖邦,等.肾透明细胞癌常规超声和超声造影特征及其与病理分化程度的相关性[J].中国超声医学杂志,2014,30(6):534-537.
[23] 于浩鹏,李 谋,张 琳,等.CT图像纹理分析评估胰腺神经内分泌肿瘤的病理分级[J].中国临床医学影像杂志,2018,29(11):34-36.

相似文献/References:

[1]王迎春,孔延亮,蔚文祥,等.家庭聚集性新型冠状病毒肺炎患者初次就诊临床检验与CT特征分析[J].陕西医学杂志,2020,49(4):392.
　WANG Yingchun,KONG Yanliang,WEI Wenxiang,et al.Laboratory examination and CT features of family aggregative corona virus disease 2019 patients at first visit[J].,2020,49(3):392.

更新日期/Last Update: 2020-03-25