Performance of Radiomics Based Multi-Parameter Models Derived from Lung CT in Differentiating Benign Non-Inflammatory, Inflammatory and Malignant Pulmonary Nodule

Abstract

Pulmonary nodules are a significant clinical issue that require accurate and efficient diagnosis. This study constructed a machine learning model, combining radiomics features of chest CT sequences with three types of microvascular density (MVD) values, to differentiate benign, inflammatory and malignant pulmonary nodules. A total of 100 patients with lung nodules on CT images and corresponding pathological results were retrospectively included in the study. The MVD values and radiomics features were calculated and extracted based on the segmented nodules. Univariate correlation analysis and principal component analysis were performed to select radiomics features. Combined MVD values and selected radiomics features, we conducted a logistic regression classification model. The area under the curve (AUC) was applied to show model performance. Our model reached an AUC value of 0.867 when tested on independent datasets. The performance of the model to differentiate benign, malignant and inflammatory nodules reached AUC values of only 0.908, 0.833, and 0.730, respectively. We conducted a prediction model that shows promising results in distinguishing three different types of lung nodules.