An Iterative Framework for Registration and Segmentation of Dynamic Three-Dimensional MR Renography
Song T, Lee V, Laine A, Wong S, Rusinek H
Our purpose was to develop a computer aided iterative registration and segmentation algorithms and to evaluate them four 4-D MR renography datasets. Without decoupling registration and segmentation problem, we achieved satisfied results in that refined average translation error was almost within half a voxel and rotation error was less than one degree. Compared with two manual segmented ROIs, computer calculated ROIs showed consistent and accurate results in overlaps and volumes.