Spatialoral variability of radiomic features and its effect on the classification of lung cancer histology

作     者：Lafata, Kyle Cai, Jing Wang, Chunhao Hong, Julian Kelsey, Chris R Yin, Fang-Fang 

作者机构：Department of Radiation Oncology Duke University Medical Center DUMC-Box 3295 DurhamNC27710 United States Medical Physics Graduate Program Duke University 2424 Erwin Road DurhamNC27705 United States Department of Health Technology and Informatics Hong Kong Polytechnic University Hong Kong Hong Kong 

出 版 物：《Physics in Medicine and Biology》 (Phys. Med. Biol.)

年 卷 期：2018年第63卷第22期

核心收录：

学科分类：0710[理学-生物学] 0831[工学-生物医学工程（可授工学、理学、医学学位）] 0810[工学-信息与通信工程] 1205[管理学-图书情报与档案管理] 1001[医学-基础医学(可授医学、理学学位)] 081203[工学-计算机应用技术] 0804[工学-仪器科学与技术] 0835[工学-软件工程] 0714[理学-统计学（可授理学、经济学学位）] 0836[工学-生物工程] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 10[医学] 

基　　金：This work was partially funded by a grant from Varian Medical Systems 

主　　题：Histology 

摘      要：The purpose of this research was to study the sensitivity of Computed Tomography (CT) radiomic features to motion blurring and signal-to-noise ratios (SNR), and investigate its downstream effect regarding the classification of non-small cell lung cancer (NSCLC) histology. Forty-three radiomic features were considered and classified into one of four categories: Morphological, Intensity, Fine Texture, and Coarse Texture. First, a series of simulations were used to study feature-sensitivity to changes in spatialoral resolution. A dynamic digital phantom was used to generate images with different breathing amplitudes and SNR, from which features were extracted and characterized relative to initial simulation conditions. Stage I NSCLC patients were then retrospectively identified, from which three different acquisition-specific feature-spaces were generated based on free-breathing (FB), average-intensity-projection (AIP), and end-of-exhalation (EOE) CT images. These feature-spaces were derived to cover a wide range of spatialoral tradeoff. Normalized percent differences and concordance correlation coefficients (CCC) were used to assess the variability between the 3D and 4D acquisition techniques. Subsequently, three corresponding acquisition-specific logistic regression models were developed to classify lung tumor histology. Classification performance was compared between the different data-dependent models. Simulation results demonstrated strong linear dependences (p 0.95) between respiratory motion and morphological features, as well as between SNR and texture features. The feature Short Run Emphasis was found to be particularly stable to both motion blurring and changes in SNR. When comparing FB-to-EOE, 37% of features demonstrated high CCC agreement (CCC 0.8), compared to only 30% for FB-to-AIP. In classifying tumor histology, EoE images achieved an average AUC, Accuracy, Sensitivity, and Specificity of , respectively. FB images achieved respective values of , an