Contourlet Textual Features: Improving the Diagnosis of Solitary Pulmonary Nodules in Two Dimensional CT Images

Abstract

ObjectiveTo determine the value of contourlet textural features obtained from solitary pulmonary nodules in two dimensional CT images used in diagnoses of lung cancer.Materials and MethodsA total of 6,299 CT 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). Further to this, nineteen patient information categories, which included seven demographic parameters and twelve morphological features, were also collected. A contourlet was used to extract fourteen types of textural features. These were then used to establish three support vector machine models. One comprised a database constructed of nineteen collected patient information categories, another included contourlet textural features and the third one contained both sets of information. 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 were used as the assessment criteria. In addition, the synthetic minority over-sampling technique (SMOTE) was used to preprocess the unbalanced data.ResultsUsing 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. These results were higher than results derived using the database without textural features (0.82, 0.47, 0.74, 0.67, 0.84, 0.29, and 0.83 respectively) as well as the database comprising only textural features (0.81, 0.64, 0.67, 0.72, 0.88, 0.44, and 0.85 respectively). Using the SMOTE as a pre-processing procedure, new balanced database generated, including observations of 5,816 benign ROIs and 5,815 malignant ROIs, and accuracy was 0.93.ConclusionOur results indicate that the combined contourlet textural features of solitary pulmonary nodules in CT images with patient profile information could potentially improve the diagnosis of lung cancer.

Clinical applications of textural analysis in non-small cell lung cancer

“…When textural features were combined with clinical and CT features, differentiating performance significantly increased from 79 to 92.9% (p < 0.05). As with the previous study, Wang et al 68 showed that TA can improve diagnostic certainty. In contrast to the previous study, this study analysed the whole tumour, instead of a single image slice.…”

Performance Evaluation of a Deep Learning System for Differential Diagnosis of Lung Cancer With Conventional CT and FDG PET/CT Using Transfer Learning and Metadata

“…These studies used texture analysis with machine learning, 2-or 3-dimensional (3D) convolutional neural network (CNN), residual network, ensemble method, and transfer learning (TL) on CT images to classify lung nodules. [8][9][10][11][12][13][14][15][16][17] The TL method uses an unconnected training set to preconfigure the CNN to reduce the size of the specific training set. 18 It allows more effective learning about new things based on pretrained weights from a large image data set.…”

“…Recently, several studies using deep learning or machine learning approaches to diagnose lung cancer with conventional CT and FDG PET/CT have been published. These studies used texture analysis with machine learning, 2- or 3-dimensional (3D) convolutional neural network (CNN), residual network, ensemble method, and transfer learning (TL) on CT images to classify lung nodules 8–17 . The TL method uses an unconnected training set to preconfigure the CNN to reduce the size of the specific training set 18 .…”