Evaluation of Radiomics and Machine Learning for Classifying Pulmonary Nodules in CT Images

Abstract

Lung cancer is a deadly disease which has high occurrence and death rates, worldwide. Computed Tomography (CT) imaging is being widely used by clinicians for detection of lung cancer. Radiomics extracted from medical images together with Machine Learning (ML) platform has given encouraging results in lung cancer diagnosis. Therefore, this study is proposed with the aim to efficiently apply and evaluate radiomics and ML techniques to classify pulmonary nodules in CT images. Lung Image Data Consortium is utilized in which nodules are given malignancy score 1 through 5 i.e. benign through malignant. Three scenarios are created randomly using these groups: G54 Vs G12, G543 Vs G12, and G54 Vs G123. Radiomics are extracted using Shape, Gray Level Co-occurrence Method, Gray Level Difference Method, and Gray Level Run Length Matrix along with Wavelet Packet Transform. To select a relevant set of features, four techniques i.e. Chi-square test, Analysis of variance, boosted ensemble classification tree and bagged ensemble classification tree are applied. The classification of nodule into benign or malignant is evaluated by using six models of Support vector machine. The results, in Scenario 1, show that MGSVM+Chi-square yields the best outcome compared to rest of the models with 75.3% accuracy, 77.9% sensitivity and 71.5% specificity. In Scenario 2, QSVM+Chi-square yields the best outcome compared to rest of the models with 74.7% accuracy, 70.3% sensitivity and 77.4% specificity. And in Scenario 3, CSVM+BACET yields comparatively better results with70.3% accuracy, 70.6% sensitivity and 62.1% specificity.