计算机科学 ›› 2019, Vol. 46 ›› Issue (1): 285-290.doi: 10.11896/j.issn.1002-137X.2019.01.044

所属专题: 医学图像

• 图形图像与模式识别 • 上一篇    下一篇

基于放射组学特征的胃肠道间质瘤的分类预测

刘平平1, 张文华1, 卢振泰1, 陈韬2, 李国新2   

  1. (南方医科大学医学图像处理重点实验室 广州510515)1
    (南方医科大学南方医院普外科广东省微创外科工程中心 广州510515)2
  • 收稿日期:2017-12-12 出版日期:2019-01-15 发布日期:2019-02-25
  • 作者简介:刘平平(1990-),女,硕士,主要研究方向为医学图像处理;张文华(1992-),男,硕士,主要研究方向为医学图像处理;卢振泰(1981-),男,副教授,硕士生导师,主要研究方向为医学图像处理,E-mail:luzhentai@163.com(通信作者);陈 韬(1983-),男,博士,主要研究方向为计算机辅助医学及微创胃肠外科;李国新(1966-),男,教授,主要研究方向为微创胃肠外科基础与临床研究及肿瘤应用分子病理学。
  • 基金资助:
    广东省自然科学基金(2014A030313316,2016A030313574)资助

Prediction of Malignant and Benign Gastrointestinal Stromal Tumors Based on Radiomics Feature

LIU Ping-ping1, ZHANG Wen-hua1, LU Zhen-tai1, CHEN Tao2, LI Guo-xin2   

  1. (Key Lab for Medical Imaging,Southern Medical University,Guangzhou 510515,China)1
    (Guangdong Provincial Engineering Technology Research Center of Minimally Invasive Surgery,Department of
    General Surgery,Nanfang Hospital,Southern Medical University,Guangzhou 510515,China)2
  • Received:2017-12-12 Online:2019-01-15 Published:2019-02-25

摘要: 胃肠道间质瘤(GastroIntestinal Stromal Tumors,GIST)是常见的胃肠道肿瘤,具有非定向分化特征,缺乏特异性,且具有恶性潜能,所以GIST的良恶性诊断是临床较为关注的问题。然而,病理活检及CT检查等临床鉴别手段在研究肿瘤异质性方面存在一定困难。文中提出一种基于CT图像提取大量量化的放射组学特征并利用SVM分类器对GIST良恶性进行分类预测的非侵入式方法。首先,应用放射组学方法对120个患有GIST的病人的CT图像肿瘤区域分别提取4个非纹理特征和43个纹理特征。然后,应用基于ReliefF的前向选择算法进行特征选择,再用最佳特征子集训练得到的SVM分类器来对GIST良恶性进行分类预测。实验中,共有14个纹理特征入选最佳特征子集,且SVM分类模型对GIST良恶性分类的AUC、准确率、敏感性、特异性在训练集中分别为0.9949,0.9277,0.9537,0.9018;在测试集中分别为0.8524,0.8313,0.8197,0.8420。该方法以放射组学的研究方法建立的模型,为GIST良恶性预测提供了一种非入侵式的检测手段,有望成为一种辅助诊断工具,以提高临床GIST良恶性诊断的准确率。

关键词: 放射组学, 特征选择, 胃肠道间质瘤, 支持向量机

Abstract: Gastrointestinal stromal tumors(GIST) are the most common mesenchymal tumors of the gastrointestinal tract with non-directional differentiation,varying malignancy potential and deficient specificity.Therefore,it is a more concerned issue to diagnosis benign or malignant of GIST.However,it is relatively difficult to use pathological biopsy and CT imaging to study solid tumors heterogeneity.This paper proposed a noninvasive method based on a large number of quantitative radiomics features extracted from CT images and SVM classifier to discriminate benign or malignant of GIST.120 patients with GISTs were enrolled in this retrospective study.Firstly,four non-texture features (shape features) and forty-three texture features were extracted from the tumour region of CT images of each patiant.For the initial feature set,ReliefF and forward selection were executed sequentially to feature selection.Then,SVM classifier was trained by the optimal feature subset for benign or malignant discrimination of GIST.14 texture features were selected for the optimal feature subset from the original feature set.The AUC,accuracy,sensitivity and specificity of the model were 0.9949,0.9277,0.9537 and 0.9018 in the training set,and 0.8524,0.8313,0.8197 and 0.8420 in the test set.The model established by the radiomics method provides a noninvasive detection method for predicting the benign or malignant of GIST,and this mothed maybe as an auxiliary diagnosis tool to improve the accuracy efficiently for malignant and benign discrimination of GIST.

Key words: Feature selection, Gastrointestinal stromal tumors, Radiomics, Support vector machine

中图分类号: 

  • TP391
[1]MIETTINEN M,SARLOMO-RIKALA M,LASOTA J.Gastrointestinal stromal tumors:recent advances in understanding of their biology[J].Human Pathology,1999,30(10):1213-1220.<br /> [2]LEVY A D,REMOTTI H E,THOMPSON W M,et al.Gastrointestinal stromal tumors:radiologic features with pathologic correlation[J].Radiographics,2003,23(2):283-304.<br /> [3]WARNER N E.Ackerman’s Surgical Pathology[J].Journal of the American Medical Association,1997,277(4):345-345.<br /> [4]DEMETRI G D,BENJAMIN R,BLANKE C D,et al.NCCN Task Force report:optimal management of patients with gastrointestinal stromal tumor (GIST)-expansion and update of NCCN clinical practice guidelines[J].Journal of the National Comprehensive Cancer Network,2004,2(1):1-29.<br /> [5]LONGO D L.Tumor heterogeneity and personalized medicine[J].New England Journal of Medicine,2012,366(10):956-958.<br /> [6]LAMBIN P,RIOSVELAZQUEZ E,LEIJENAAR R,et al.Radiomics:Extracting more information from medical images using advanced feature analysis[J].European Journal of Cancer,2012,48(4):441-446.<br /> [7]GILLIES R J,KINAHAN P E,HRICAK H.Radiomics:Images Are More than Pictures,They Are Data[J].Radiology,2016,278(2):563-577.<br /> [8]KUMAR V,GU Y,BASU S,et al.Radiomics:the process and the challenges[J].Magnetic Resonance Imaging,2012,30(9):1234-1248.<br /> [9]GUO W,LI H,ZHU Y,et al.Prediction of clinical phenotypes in invasive breast carcinomas from the integration of radiomics and genomics data[J].Journal of Medical Imaging,2015,2(4):1-12.<br /> [10]VALLIÈRES M,FREEMAN C R,SKAMENE S R,et al.A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities[J].Physics in Medicine & Biology,2015,60(14):5471-5496.<br /> [11]HUANG Y Q,LIANG C H,HE L,et al.Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer[J].Science Foundation in China,2016,34(4):2157-2164.<br /> [12]JOENSUU H.Risk stratification of patients diagnosed with gastrointestinal stromal tumor[J].Human Pathology,2008,39(10):1411-1419.<br /> [13]HARALICK R M,SHANMUGAM K,DINSTEIN I H.Textural Features for Image Classification[J].IEEE Transactions on Systems Man & Cybernetics,1973,smc-3(6):610-621.<br /> [14]BOCCHINO C,CARABELLESE A,CARUSO T,et al.Use of gray value distribution of run lengths for texture analysis[J].Pattern Recognition Letters,1990,11(6):415-419.<br /> [15]DASARATHY B V,HOLDER E B.Image characterizations based on joint gray level-run length distributions[J].Pattern Recognition Letters,1991,12(8):497-502.<br /> [16]THIBAULT G,FERTIL B,NAVARRO C,et al.Texture Indexes and Gray Level Size Zone Matrix Application to Cell Nuclei Classification[C]//Pattern Recognition and Information Processing (PRIP).2009:140-145.<br /> [17]AMADASUN M,KING R.Textural features corresponding to textural properties[J].IEEE Transactions on Systems Man & Cybernetics,1989,19(5):1264-1274.<br /> [18]DOUGHERTY E R,HUA J,SIMA C.Performance of feature selection methods[J].Current Genomics,2009,10(6):365-374.<br /> [19]KIRA K,RENDELL L A.The feature selection problem:traditional methods and a new algorithm[C]//Tenth National Conference on Artificial Intelligence.California:AAAI Press,1992:129-134.<br /> [20]ROBNIK,IKONJA M,KONONENKO I.Theoretical and Empirical Analysis of ReliefF and RReliefF[J].Machine Learning,2003,53(1-2):23-69.<br /> [21]VAPNIK V N.The nature of statistical learning theory[M].Germany:Springer,2000:988-999.<br /> [22]SCHÖLKOPF B,TSUDA K,VERT J.Kernel methods in computational biology[J].Bussei Kenkyu,2004,81(97):35-90.<br /> [23]CHANG Y W,HSIEH C J,CHANG K W,et al.Training and Testing Low-degree Polynomial Data Mappings via Linear SVM[J].Journal of Machine Learning Research,2010,11(11):1471-1490.<br /> [24]SWETS J A.Signal detection theory and ROC analysis in psychology and diagnostics:Collected papers[M].England:Lawrence Erlbaum Associates,1996:840-841.<br /> [25]PERES D J,IUPPA C,CAVALLARO L,et al.Significant wave height record extension by neural networks and reanalysis wind data[J].Ocean Modelling,2015,94(5):128-140.<br /> [26]ALTMAN D G,BLAND J M.Diagnostic Tests 1:Sensitivity and Specificity[J].BMJ British Medical Journal,1994,308(6943):1552.<br /> [27]METZ C E.Basic principles of ROC analysis[J].Seminars in Nuclear Medicine,1978,8(4):283-298.<br /> [28]ZAFFALON M,HUTTER M.Robust Feature Selection by Mutual Information Distributions[J].Computer Science,2014:577-584.<br /> [29]ROFFO G,MELZI S.Feature Selection via Eigenvector Centrality[C]//New Frontiers in Mining Complex Patterns in Conjunction with ECML/PKDD.2016.<br /> [30]GU Q,LI Z,HAN J.Generalized Fisher score for feature selection[C]//Twenty-Seventh Conference on Uncertainty in Artificial Intelligence.2011:266-273.<br /> [31]GUYON I,WESTON J,BARNHILL S,et al.Gene Selection for Cancer Classification using Support Vector Machines[J].Machine Learning,2002,46(1-3):389-422.<br /> [32]EFRON B.Bootstrap Methods:Another Look at the Jackknife[J].Annals of Statistics,1979,7(1):1-26.
[1] 李斌, 万源.
基于相似度矩阵学习和矩阵校正的无监督多视角特征选择
Unsupervised Multi-view Feature Selection Based on Similarity Matrix Learning and Matrix Alignment
计算机科学, 2022, 49(8): 86-96. https://doi.org/10.11896/jsjkx.210700124
[2] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[3] 单晓英, 任迎春.
基于改进麻雀搜索优化支持向量机的渔船捕捞方式识别
Fishing Type Identification of Marine Fishing Vessels Based on Support Vector Machine Optimized by Improved Sparrow Search Algorithm
计算机科学, 2022, 49(6A): 211-216. https://doi.org/10.11896/jsjkx.220300216
[4] 陈景年.
一种适于多分类问题的支持向量机加速方法
Acceleration of SVM for Multi-class Classification
计算机科学, 2022, 49(6A): 297-300. https://doi.org/10.11896/jsjkx.210400149
[5] 侯夏晔, 陈海燕, 张兵, 袁立罡, 贾亦真.
一种基于支持向量机的主动度量学习算法
Active Metric Learning Based on Support Vector Machines
计算机科学, 2022, 49(6A): 113-118. https://doi.org/10.11896/jsjkx.210500034
[6] 康雁, 王海宁, 陶柳, 杨海潇, 杨学昆, 王飞, 李浩.
混合改进的花授粉算法与灰狼算法用于特征选择
Hybrid Improved Flower Pollination Algorithm and Gray Wolf Algorithm for Feature Selection
计算机科学, 2022, 49(6A): 125-132. https://doi.org/10.11896/jsjkx.210600135
[7] 邢云冰, 龙广玉, 胡春雨, 忽丽莎.
基于SVM的类别增量人体活动识别方法
Human Activity Recognition Method Based on Class Increment SVM
计算机科学, 2022, 49(5): 78-83. https://doi.org/10.11896/jsjkx.210400024
[8] 储安琪, 丁志军.
基于灰狼优化算法的信用评估样本均衡化与特征选择同步处理
Application of Gray Wolf Optimization Algorithm on Synchronous Processing of Sample Equalization and Feature Selection in Credit Evaluation
计算机科学, 2022, 49(4): 134-139. https://doi.org/10.11896/jsjkx.210300075
[9] 孙林, 黄苗苗, 徐久成.
基于邻域粗糙集和Relief的弱标记特征选择方法
Weak Label Feature Selection Method Based on Neighborhood Rough Sets and Relief
计算机科学, 2022, 49(4): 152-160. https://doi.org/10.11896/jsjkx.210300094
[10] 武玉坤, 李伟, 倪敏雅, 许志骋.
单类支持向量机融合深度自编码器的异常检测模型
Anomaly Detection Model Based on One-class Support Vector Machine Fused Deep Auto-encoder
计算机科学, 2022, 49(3): 144-151. https://doi.org/10.11896/jsjkx.210100142
[11] 李宗然, 陈秀宏, 陆赟, 邵政毅.
鲁棒联合稀疏不相关回归
Robust Joint Sparse Uncorrelated Regression
计算机科学, 2022, 49(2): 191-197. https://doi.org/10.11896/jsjkx.210300034
[12] 张叶, 李志华, 王长杰.
基于核密度估计的轻量级物联网异常流量检测方法
Kernel Density Estimation-based Lightweight IoT Anomaly Traffic Detection Method
计算机科学, 2021, 48(9): 337-344. https://doi.org/10.11896/jsjkx.200600108
[13] 杨蕾, 降爱莲, 强彦.
基于自编码器和流形正则的结构保持无监督特征选择
Structure Preserving Unsupervised Feature Selection Based on Autoencoder and Manifold Regularization
计算机科学, 2021, 48(8): 53-59. https://doi.org/10.11896/jsjkx.200700211
[14] 侯春萍, 赵春月, 王致芃.
基于自反馈最优子类挖掘的视频异常检测算法
Video Abnormal Event Detection Algorithm Based on Self-feedback Optimal Subclass Mining
计算机科学, 2021, 48(7): 199-205. https://doi.org/10.11896/jsjkx.200800146
[15] 胡艳梅, 杨波, 多滨.
基于网络结构的正则化逻辑回归
Logistic Regression with Regularization Based on Network Structure
计算机科学, 2021, 48(7): 281-291. https://doi.org/10.11896/jsjkx.201100106
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!