Objective: To determine the value of contourlet textural features obtained from solitary pulmonary nodules in CT images used in diagnoses of lung cancer.Materials and methods:A total of 6,229CT images were acquired from 336 patients, with 1,454 benign pulmonary nodule images from 84 patients (50 male, 34 female) and 4,845 malignant from 252 patients (150 male,102 female).Besides, nineteen patient information categories, including seven demographic parameters and twelve morphological features, were collected.A contourlet was used to extract fourteen types of textural features and three support vector machine models were established using one database containing nineteen patient information categories, one included contourlet textural features and the third one contained both.Ten-fold cross-validation was used to evaluate the diagnosis results for the three databases, with sensitivity, specificity, accuracy, the area under the curve (AUC), precision, Youden index, and F-measure used as the assessment criteria.Results:Using a database containing textural features and patient information, sensitivity, specificity,accuracy, AUC, precision, Youden index, and F-measure were: 0.95, 0.71, 0.89, 0.89, 0.92, 0.66,and 0.93 respectively, which were all higher than those using database without textural features (0.82, 0.47, 0.74, 0.67, 0.84, 0.29, and 0.83 respectively) or just containing textural features (0.81,0.64, 0.67, 0.72, 0.88, 0.44, and 0.85 respectively).Conclusions: Combined contourlet textural features of solitary pulmonary nodules in CT images could improve the diagnosis of lung cancer.
Textural feature Contourlet Support Vector Machine Solitary Pulmonary nodule
Jingjing Wang Tao Sun Ni Gao Desmond Dev Menon Yanxia Luo Qi Gao Xia Li Wei Wang Huiping Zhu Pingxin Lv Zhigang Liang Lixin Tao Lei Pan Tao Zhou Xiangtong Liu Xiuhua Guo
School of Public Health, Capital Medical University, Beijing 100069, China;Beijing Municipal Key Lab School of Medical Sciences, Edith Cowan University, Joondalup, WA6027, Australia;School of Exercise School of Public Health, Capital Medical University, Beijing 100069, China;Department of Epidemiolog School of Public Health, Capital Medical University, Beijing 100069, China;Beijing Municipal Key Lab Department of Radiology, Beijing Chest Hospital, Capital Medical University, Beijing 101149, China Department of Radiology, Xuanwu Hospital, Capital Medical University, Beijing 100053, China