Skip to Main Content
The size and growth rate of lung nodules highly correlate with the chance of malignancy and they are the most important indicators for assessment of lung cancer treatment effect. Therefore, accurate segmentation of the lung nodules is greatly significant for the diagnosis and treatment of the lung cancers. In this paper, a novel method is introduced to segment juxta-pleural nodules in CT image data for subsequent volume assessment. The novelties of this algorithm lie in two aspects. First, the algorithm utilizes the three dimensional ray casting method to extract the surface of the nodule, which is novel and efficient. Second, this algorithm employees the three dimensional distance transform method to improve the reproducibility of segmentation result and minimize the influence of the manually indicated seed point. The algorithm is tested on datasets from 39 patients with a total of 65 juxta-pleural nodules. Evaluated by the senior radiologists, this method obtains satisfactory results with segmentation accuracy exceeding 90%. Moreover, compared to the phantoms, the volume of the segmentation results highly coincide with the standard volume of the phantoms. It shows the algorithm is helpful for the segmentation, volume measurements and evaluation of juxta-pleural nodules.