Texture recognition of pulmonary nodules based on volume local direction ternary pattern

作     者：Fan, Zhipeng Sun, Huadong Ren, Cong Han, Xiaowei Zhao, Zhijie 

作者机构：Harbin Univ Commerce Sch Comp & Informat Engn Harbin 150028 Peoples R China Key Lab Elect Commerce & Informat Proc Heilongjia Harbin Heilongjiang Peoples R China 

出 版 物：《BIOENGINEERED》 (Bioengineered)

年 卷 期：2020年第11卷第1期

页      面：904-920页

核心收录：

学科分类：0710[理学-生物学] 07[理学] 09[农学] 0836[工学-生物工程] 

基　　金：Harbin Science and Technology Bureau outstanding subject leader fund project [2017RAXXJ055] Youth Project of Harbin University of Commerce [18XN022, 17XN006, 17XN003] 

主　　题：CAD random walk volume local direction ternary pattern Stacking algorithm 

摘      要：In recent years, the incidence of lung cancer has been increasing. Lung cancer detection is based on computed tomography (CT) imaging of the lung area to determine whether there are pulmonary nodules. And then judge what s good and what s bad. However, due to the traditional way of manual reading and lack of experience and other problems. This leads to visual fatigue and misdiagnosis and missed diagnosis. In order to detect pulmonary nodules early and accurately, a new assistant diagnosis method for pulmonary nodules is proposed. Firstly, the image is preprocessed and denoised by median filter, the lung parenchyma is segmented by random walk algorithm and the region of interest is extracted, and then, according to the continuity of the CT slices, the texture feature extraction method of pulmonary nodules based on volume local direction ternary pattern is used to extract the features. Finally, the pulmonary nodules are identified and classified by the assistant diagnosis model of pulmonary nodules based on Stacking algorithm. In order to illustrate the validity of the diagnosis model, the experiments are carried out by cross-validation of ten folds. Experiments using data from LIDC database show that the accuracy, sensitivity and specificity of the proposed method are 82.2%, 85.7%, and 78.8%, respectively. Texture Recognition method based on volume vocal direction ternary pattern is feasible for the identification of pulmonary nodules and provides a reference value for doctor-assisted diagnosis.