诊断学理论与实践

诊断学理论与实践 ›› 2017, Vol. 16 ›› Issue (06): 601-606.doi: 10.16150/j.1671-2870.2017.06.008

• 论著 • 上一篇    下一篇

MRI图像纹理分析在胰腺神经内分泌肿瘤病理分级中的应用研究

李旭东1a,1b, 林晓珠1a,1b, 房炜桓2, 谢环环1a,3, 陈楠1a, 柴维敏1a, 严福华1a, 陈克敏2   

  1. 1.上海交通大学医学院附属瑞金医院,a. 放射科,b. 核医学科,上海 200025;
    2.上海交通大学医学院附属瑞金北院放射科,上海 200080;
    3.浙江大学附属第二医院放射科,浙江 杭州 310009
  • 收稿日期:2017-06-20 出版日期:2017-12-25 发布日期:2017-12-25
  • 通讯作者: 林晓珠 E-mail: lxz11357@rjh.com.cn
  • 基金资助:
    国家自然科学基金资助项目（81201145）

Application of texture analysis of MR imagings in grading of pancreatic neuroendocrine neoplasms

LI Xudong1a,1b, LIN Xiaozhu1a,1b, FANG Weihuan2, XIE Huanhuan1a,3, CHEN Nan1a, CHAI Weimin1a, YAN Fuhua1a, CHEN Kemin2   

  1. 1a. Department of Radiology, 1b. Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China;
    2. Department of Radiology, Ruijin Hospital North, Shanghai Jiao Tong University School of Medicine, Shanghai 200080, China;
    3. Department of Radiology, the Second Affiliated Hospital of Zhejiang University, Zhejiang Hangzhou 310009, China
  • Received:2017-06-20 Online:2017-12-25 Published:2017-12-25

PDF (PC)

158

摘要： 目的: 探讨MRI图像纹理分析在胰腺神经内分泌肿瘤分级中的应用价值。方法: 回顾性分析我院64例经手术或病理活检确诊为神经内分泌肿瘤患者的MRI图像,运用MaZda软件通过手动勾画感兴趣区（region of inte-rest,ROI）的方式提取病变的纹理特征,通过特征选择方法选出最具鉴别胰腺神经内分泌肿瘤病理分级的纹理特征,方法包括Fisher系数（Fisher coefficient,Fisher）、分类错误概率联合平均相关系数（classification error probability combined average correlation coefficients,POE+ACC）、互信息（mutual information,MI）及上述3种方法的联合法（FPM）。用特征分类统计方法,判别3种病理分级（G1、G2、G3）,结果以判错率形式表示。结果: 特征选择方法中,3种方法联合法（FPM）选择的纹理特征鉴别3种病理分级的判错率最低,为9.38%（6/64）;特征统计方法中,非线性判别分析（nonlinear discriminant analysis,NDA）区分G1、G2、G3 3种分级的判错率要低于原始数据分析（raw data analysis,RDA）、主成分分析（principal component analysis,PCA）、线性判别分析（linear discriminant analysis,LDA）。各序列中,表观弥散系数(apparent diffusion coefficient, ADC)图纹理分析判错率最低,但各序列之间的差异尚无统计学意义。结论: MRI图像纹理分析可作为胰腺神经内分泌肿瘤术前分级的辅助工具,采用Fisher系数、分类错误概率联合平均相关系数（POE+ACC）和互信息（MI）3种方法联合（FPM）的MRI图像纹理特征选择技术,结合非线性判别分析（NDA）方法,有较低的错判率。

关键词: 胰腺神经内分泌肿瘤, 磁共振成像, 纹理分析, 特征选择, 病理分级

Abstract: Objective: To investigate the application of texture analysis derived from MR imaging in grading of pancreatic neuroendocrine neoplasms(PNENs). Methods: MR imagings of 64 patients with pathologically confirmed PNENs admitted to Ruijin Hospital were enrolled. Texture features were extracted from manually drawn ROIs by using MaZda software, and were selected according to the pathological grade by the feature selection methods. Statistical methods including Fisher coefficient(Fisher), classification error probability combined with average correlation coefficients(POE+ACC), mutual information(MI), and combination of above three methods(FPM) were used to classify the pathological grading of PNENs. The results were shown by misclassification rate. Results: For feature selection methods, FPM had the lowest misclassification rate. Among the statistical methods, the misclassification of NDA was lower than those of RDA, PCA, and LDA. Among the MRI sequences, the ADC map obtained the lowest misclassification rate of 9.38%(6/64), but there was no significant difference between sequences. Conclusions: Texture analysis of MR imaging can be used as an assistant tool for preoperative grading of pancreatic neuroendocrine neoplasms, and when it comes to statistical methods, FPM has the lowest misclassification rate.

Key words: Pancreatic neuroendocrine neoplasms, MRI, Texture analysis, Feature selection, Tumor grade

中图分类号: