Enhancement and detection of lung nodules with Multiscale filters in CT images

It is important to enhance and detect nodules in CT images in order to identify the lung cancer at early stage. Nodules which are included in medical image generally have multiple size and scale, and have blob-like structure. Recently, 3D multiscale filter approach is proposed for lung nodules detection. However, the 3D method take too much computing time to be applicable in real diagnose systems. In this paper, we propose a two step method for lung nodules detection in CT images. Firstly, we use 2D multiscale filter to detect the candidates of lung nodules on the slice images, and then, reduce most of false-positive nodules using logical AND operator of continuous CT slices. The effectiveness of the purposed methods has been demonstrated by experiments.