Accurate Non-rigid Registration of Lung Images Based on Mutual Information

In clinical diagnosis of lung disease, registration of lung images from different imaging systems canprovide a multi-informative image and improve its diagnostic accuracy. In this study, the originallung images were obtained from computed tomography (CT) and single-photon emission computedtomography (SPECT). After the decomposition of the images using wavelet transform, a non-rigidregistration were proposed, in which CT image was used as the reference image and SPECT imagewas used as the floating image. In registration, the mutual information between the reference andfloating images was calculated in the process of translation, rotation and elastic transformation. Atlast, the result of the registration was evaluated by the edges of the bone, muscle, thorax and lungtissues in CT and SPECT images. It showed an accuracy registration between lung CT and SPECTimages.