Micronodule Detection and False-Positive Elimination from 3D Chest CT
Computed Tomography (CT) is generally accepted as the most sensitive way for lung cancer screening. Its high contrast resolution allows the detection of small nodules and, thus, lung cancer at a very early stage. In this paper, we propose a method for automating nodule detection from high-resolution 3D chest CT images. Our method focuses on the detection of both calcified (high-contrast) and noncalcified (low-contrast) granulomatous nodules less than 5mm in diameter, using a series of 3D filters including a filter for vessels and noise suppression, a filter for nodule enhancement, and a filter for false-positive elimination based on local skeletonization of suspicious nodule areas. We also present promising results of applying our method to various clinical chest CT datasets with over 90% detection rate.