[1]张航,李清,李淑龙,等.影像组学在鉴别伴结石肾积水是否伴发肾细胞癌中的应用[J].南方医科大学学报,2019,(05):547.[doi:10.12122/j.issn.1673-4254.2019.05.08]
点击复制

影像组学在鉴别伴结石肾积水是否伴发肾细胞癌中的应用()
分享到:

《南方医科大学学报》[ISSN:1673-4254/CN:44-1627/R]

卷:
期数:
2019年05期
页码:
547
栏目:
出版日期:
2019-05-15

文章信息/Info

Title:
A radiomic approach to differential diagnosis of renal cell carcinoma in patients with hydronephrosis and renal calculi
作者:
张航李清李淑龙马建华黄静
关键词:
伴结石肾积水肾细胞癌影像组学CT、特征选择支持向量机
Keywords:
renal hydronephrosis with calculi renal cell carcinoma radiomics computed tomography feature selection support vector machine
DOI:
10.12122/j.issn.1673-4254.2019.05.08
摘要:
目的利用有监督的机器学习方法探讨影像组学分析在鉴别伴结石肾积水是否伴发肾细胞癌中的应用。方法回顾性分 析经病理确诊的66例伴结石肾积水患者的腹部CT扫描,其中31例伴发肾细胞癌。对每位患者的三维肿瘤区域提取18个非纹 理特征和344个纹理特征,并应用无限特征选择技术(InfFS)结合支持向量机分类器的方法(SVM)进行特征选择。最后将最佳 特征子集训练SVM分类器并对伴结石肾积水是否伴发肾细胞癌进行预测。结果12个纹理特征入选最佳特征子集,且SVMInfFS 对伴结石肾积水是否伴发肾肿瘤的预测结果如下:感受曲线下面积、准确率、敏感性、特异性、假阳性和假阴性分别为 0.907、81.0%、70.0%、90.9%、9.1%和30.0%。临床医生以分类结果作为辅助信息进行诊断的结果如下:准确率、敏感性、特异 性、假阳性和假阴性分别为90.5%、80.0%、100%、0.00%、20.0%。结论基于有监督机器学习的计算机辅助分类模型,可有效提 取的辅助诊断信息,提高伴结石肾积水是否伴发肾细胞癌的诊断率。
Abstract:
Objective To explore the application of radiomic analysis in differential diagnosis of renal cell carcinoma in patients with hydronephrosis and renal calculi using supervised machine learning methods. Method The abdominal CT scan data were retrospectively analyzed for 66 patients with pathologically confirmed hydronephrosis and renal calculi, among whom 35 patients had renal cell carcinoma. In each case 18 non-texture features and 344 texture features were extracted from the region of interest (ROI). Infinite feature selection (InfFS)-based forward feature selection method coupled with support vector machine (SVM) classifier was used to select the optimal feature subset. SVM was trained and performed the prediction using the selected feature subset to classify whether hydronephrosis with renal calculi was associated with renal cell carcinoma. Results A total of 12 texture features were selected as the optimal features. The area under curve (AUC), accuracy, sensitivity, specificity, false positive rate and false negative rate of the SVM-InfFS model for predicting accompanying renal tumors in patients with hydronephrosis and calculi were 0.907, 81.0%, 70.0%, 90.9%, 9.1%, and 30.0%, respectively. The diagnostic accuracy, sensitivity, specificity, false positive and false negative rates by the clinicians provided with these classification results were 90.5%, 80.0%, 100%, 0.00%, and 20.0%, respectively. Conclusion The computer-aided classification model based on supervised machine learning can effectively extract the diagnostic information and improve the diagnostic rate of renal cell carcinoma associated with hydronephrosis and renal calculi.

相似文献/References:

[1]李明,刘俊,胡卫列,等.二甲双胍对肾癌细胞凋亡的影响及机制[J].南方医科大学学报,2011,(09):1504.
[2]夏军,骆平,王晖,等.肾癌多层螺旋CT成像与肿瘤血管形成的相关性[J].南方医科大学学报,2006,(05):629.
 XIA Jun,LUO Ping,WANG Hui,et al.Correlation of multislice spiral CT findings with vascular endothelial growth factor expressions and microvessel density in renal cell carcinoma[J].Journal of Southern Medical University,2006,(05):629.
[3]白寒,郑少斌,吴京,等.血钙水平与肾癌肿瘤大小、分期的相关性分析[J].南方医科大学学报,2005,(11):1435.
 BAI Han,ZHENG Shao-bin,WU Jing,et al.Correlation of serum calcium level with tumor size and stage of renal cell carcinoma[J].Journal of Southern Medical University,2005,(05):1435.
[4]姜耀东,郑少斌,王战会.RT-PCR法检测肾癌组织中MN/CAⅨ基因表达[J].南方医科大学学报,2004,(08):925.
 JIANG Yao-dong,ZHENG Shao-bin,WANG Zhan-hui.MN/CAⅨ gene expression in renal cell carcinoma detected by RT-PCR[J].Journal of Southern Medical University,2004,(05):925.
[5]邵志强,郑少斌,肖耀军,等.缺氧诱导因子-1α和血管内皮生长因子在肾细胞癌组织中的表达及意义[J].南方医科大学学报,2005,(08):1034.
 SHAO Zhi-qiang,ZHENG Shao-bin,XIAO Yao-jun,et al.Expressions of hypoxia inducible factor-1α and vascular endothelial growth factor in human renal cell carcinoma[J].Journal of Southern Medical University,2005,(05):1034.
[6]司彤,刘春晓,许凯,等.miR-199a在肾细胞癌中的表达与临床病理特征及预后的关系[J].南方医科大学学报,2012,(11):1568.
[7]张琳,李玲,孔海瑞,等.基于气相色谱质谱技术的肾细胞癌患者尿液代谢组学分析[J].南方医科大学学报,2015,(05):763.

更新日期/Last Update: 1900-01-01