A Novel Method for Lung Nodule Segmentation Based on CT Images

Computed tomography (CT) has unconquerable advantage over other imaging techniques for detecting lung nodules. The size and the growth rate of lung nodules are the most important indicators for the maglignancy of a lung cancer. Therefore, the accurate segmentation of the lung nodules is of great significance for the diagnosis of the lung cancers. In this paper, we propose a novel method for the segmentation of lung nodules in CT image data for subsequent volume assessment. The distinguishing features of our algorithm are as follows. 1) The user interaction process, such as the selection of the seed point and the adjustment of the volume of interest. This operation can make best use of the knowledge of the radiologists. 2) Its strong adaptive capacity. It can cope with four kind's nodules including isolated solid nodules, juxta-vascular nodules, ground glass opacities and juxta-pleural nodules properly. We test our algorithm on datasets from 85 patients with a total of 232 nodules. The segmentation accuracy exceeds 90% on average. The achieved results support the use of the proposed algorithm for volume measurements of lung nodules examined with low-dose CT scanning technique.