Purpose. To performlung image registration for reducing misregistration artifacts on three-dimensional (3D) temporal subtraction\nof chest computed tomography (CT) images, in order to enhance temporal changes in lung lesions and evaluate these changes after\ndeformable image registration (DIR). Methods. In 10 cases, mutual information (MI) lung mask affine mapping combined with\ncross-correlation (CC) lung diffeomorphicmapping was used to implement lung volume registration.With advanced normalization\ntools (ANTs), we used greedy symmetric normalization (greedy SyN) as a transformation model, which involved MI-CC-SyN\nimplementation. The resulting displacement fields were applied to warp the previous (moving) image, which was subsequently\nsubtracted from the current (fixed) image to obtain the lung subtraction image. Results. The average minimum and maximum\nlog-Jacobians were 0.31 and 3.74, respectively.When considering 3D landmark distance, the root-mean-square error changed from\nan average of 20.82mm for
Loading....