Lung segmentation of sagittal and coronal MR images using morphological operations

Abstract

In this work, segmentation is an intermediate step in the registration and 3D reconstruction of the lung. New MR imaging protocols have been used to enhance the lung internal structures and, consequently, the lung boundary is weakened. This fact turns the segmentation of lung MR images particularly difficult. The algorithm proposed herein uses morphological operators to segment sagittal and coronal lung MR images. The algorithm is tested with several sagittal and coronal temporal sequences of MR images. Using the resulting segmentation, lung masks are created to determine the region with high probability where the lung contour is. The masks were used in a temporal segmentation algorithm based on Hough transform to determine the lung boundary with higher precision. The results showed to be robust and consistent under the MR temporal image sets tested.