Lung nodule detection using template matching and similarity measurement

Abstract

In this study, we developed a computer aided detection system (CAD) to detect lung nodules on computed tomography images. Template matching and similarity measurement methods used for examine whether region of interest which extracted using image pre-processing techniques are nodule candidate. Intensity thresholding, distance thresholding, neighbourhood analysis are preprocessing techniques of the developed CAD system. Pearson's correlation coefficient, simple matching coefficient, Jaccard's coefficient, Euclidean Distance and Sokal & Sneath similarity coeeficient calculated to measure similarity between nodule candidate and the template. Sensitivity of the CAD and number of false positives per slice are given in conclusion.