A Semi-automatic Solitary Pulmonary Nodule Volume Measurement Algorithm on Low-Dose CT Images

Abstract

The computer-assisted methods for measuring and tracking nodule volumes have the potential to improve precision for indicating of malignancy for indeterminate nodules. In this paper, we propose a semi-automatic geometric solitary pulmonary nodule (SPN) volume measurement algorithm for calculating the precise volume of indeterminate SPNs with low-dose CT (LDCT) images. The algorithm divided the SPN volume into three parts: the SPN core, the parenchymal area, and the partial volume area. Then we calculated the volume with a geometry method and corrected the volume for partial volume effects with the partial volume area. The proposed method has been compared with the manual volume measurement of nodules by radiologists using two sets CT images in vivo. The result shows that the method is more objective and can evaluate the indeterminate nodules growth rate effectively using LDCT images.