Lung Parenchyma Segmentation Based on Contourlet Transform and Harris Corner Detection

This paper presents a new automatic lung segmentation method. Harris corner detection algorithm is used to solve the problem of separating the left lung from the right one, and contourlet transform and mathematical morphology hybrid algorithm are used to solve the problem that the nodules at lung edge is easy to be missed. Through the simulation results of multiple lung CT images, compared with the common algorithms, the results show that the average sensitivity and average accuracy become much better.