Hybrid Classification Approach of Malignant and Benign Pulmonary Nodules Based on Topological and Histogram Features

This paper focuses on an approach for characterizing the internal structure which is one of important clues for differentiating between malignant and benign nodules in three-dimensional (3-D) thoracic images. In this approach, each voxel was described in terms of shape index derived from curvatures on the voxel. The voxels inside the nodule were aggregated via shape histogram to quantify how much shape category was present in the nodule. Topological features were introduced to characterize the morphology of the cluster constructed from a set of voxels with the same shape category. The properties such as curvedness and CT density were also built into the representation. In the classification step, a hybrid unsupervised/supervised structure was performed to improve the classifier performance. It combined the k-means clustering procedure and the linear discriminate (LD) classifier. The performance of the hybrid classifier was compared to that of LD classifier alone. Receiver operating characteristics (ROC) analysis was used to evaluate the accuracy of the classifiers. We also compared the performance of the hybrid classifier with those of physicians. The classification performance reached the performance of physicians. Our results demonstrate the feasibility of the hybrid classifier based on the topological and histogram features to assist physicians in making diagnostic decisions.