Automatic benign and malignant classification of pulmonary nodules in thoracic computed tomography based on RF algorithm. Issue 7 (1st July 2018)

• Record Type: Journal Article
• Authors: Li, Xiang‐Xia; Li, Bin; Tian, Lian‐Fang; Zhang, Li
• Is Part Of: IET image processing. Volume 12:Issue 7(2018)
• Page Start: 1253
• Page End: 1264
• Publication Date: 2018-07-01
• Subjects: image segmentation -- image classification -- medical image processing -- lung -- Gabor filters -- feature extraction -- cancer -- image texture -- computerised tomography; malignant classification -- RFs algorithm -- malignant pulmonary nodules -- lung cancer -- improved random forest algorithm -- thoracic computed tomography images -- geometric texture features -- rotation invariant uniform local binary pattern -- Gabor filter methods -- malignant nodules -- bootstrap method -- classification method -- lung images dataset consortium dataset -- benign pulmonary nodules -- random walk algorithm -- pulmonary nodule segmentation -- feature vector -- RF classifier -- feature subset -- General Hospital of Guangzhou Military Command; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2016.1014
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Classification of benign and malignant pulmonary nodules can provide useful indicators for estimating the risk of lung cancer. In this study, an improved random forest (RF) algorithm is proposed for classification of benign and malignant pulmonary nodules in thoracic computed tomography images. First, an improved random walk algorithm is proposed to automatically segment pulmonary nodules. Then, intensity, geometric and texture features based on the grey‐level co‐occurrence matrix, rotation invariant uniform local binary pattern and Gabor filter methods are combined to generate an effective and discriminative feature vector. Mutual information is employed to reduce the dimensionality. Finally, an improved RF classifier is trained to classify benign and malignant nodules. An appropriate feature subset is selected by the bootstrap method and an effective combination method is introduced to predict a class label. The proposed classification method on the lung images dataset consortium dataset achieves a sensitivity of 0.92 and the area under the receiver‐operating‐characteristic curve of 0.95. An additional evaluation is performed on another dataset coming from General Hospital of Guangzhou Military Command. A mean sensitivity and a mean specificity of the proposed method are 0.85 and 0.82, respectively. Experimental results demonstrate that the proposed method achieves the satisfactory classification performance.