Research on Modified Fuzzy C-means Algorithm in Lung Nodules Computer-aided Diagnosis (CAD) System

It is important for the early diagnosis and treatment of lung cancer in the Computer-aided Diagnosis/Detection (CAD) system, and accurate segmentation of pulmonary nodules from tomographic images is the basic and active research problem for the benign or malign diagnosis. For this reason, this work seeks to develop automatic detection and classification method of lung nodules. First, the algorithm separates lung parenchyma from the anatomical structures based on maximum between-cluster variance, image dilation and erosion. Secondly, a modified robust fuzzy c-means clustering(rFCM) segmentation algorithm is proposed, this method improves the objective function by adding a punishment factor, for eliminating the influence from noise and non-uniform gray problem. Experimental results have shown that the proposed method can achieve more accurate segmentation and perform better than other traditional algorithms in classification and recognition, Furthermore, the segmentation results on brain images also get a satisfied performance.