Characterization of solid pulmonary nodules using three-dimensional features

With the development of high-resolution, multirow-detector CT scanners, the prospects for diagnosing and treating lung cancer at an early stage are much improved. However, it is often difficult to determine whether a nodule, especially a small nodule, is malignant from a single CT scan. We developed a computer-aided diagnostic algorithm to distinguish benign from malignant solid nodules based on features that can be extracted from a single CT scan. Our method uses 3D geometric and densitometry moment analysis of a segmented nodule image and surface curvature from a polygonal surface model of the nodule. After excluding features directly related to size, we computed a total of 28 features. Prior to classification, the number of features was reduced through stepwise feature selection. The features are used by two classifiers, k-nearest-neighbors (k-NN) and logistic regression. We used 48 malignant nodules whose status was determined by biopsy or resection, and 55 benign nodules determined to be clinically stable through two years of no change or biopsy. The k-NN classifier achieved a sensitivity of 0.81 with a specificity of 0.76, while the logistic regression classifier achieved a sensitivity of 0.85 and a specificity of 0.80.