Novel Multistage Three-Dimensional Medical Image Segmentation: Methodology and Validation

Abstract

In this paper, we propose a novel multistage method for three-dimensional (3-D) segmentation of medical images and a new radial distance-based segmentation validation approach. For the 3-D segmentation method, we first employ a morphological recursive erosion operation to reduce the connectivity between the region of interest and its surrounding neighborhood; then we design a hybrid segmentation method to achieve an initial result. The hybrid approach integrates an improved fast marching method and a morphological reconstruction algorithm. Finally, a morphological recursive dilation is employed to recover any lost structure from the first stage of the multistage method. This approach is tested on 12 CT and 3 MRI images of the brain, heart, and kidney, to demonstrate the effectiveness and accuracy of this technique across a variety of imaging modalities and organ systems. In order to validate the multistage segmentation method, a novel radial distance-based validation method is proposed that uses a global accuracy (GA) measure. The GA is calculated based on local radial distance errors (LRDE), where LRDE are calculated on the radii emitted from points along the skeleton of the object rather than the centroid, in order to accommodate more complicated organ structures. The experimental results demonstrate that the proposed multistage segmentation method is fast and accurate, with comparable performance to existing segmentation methods, but with a significantly higher execution speed.

Nephroblastoma Analysis in Mri Images

“…In (Sachdeva et al, 2012), Sachdeva used a content-based active contour (CBAC) texture and intensity information to evolve an active contour toward the tumour boundary edge in MRI scans. Gu et al (Gu et al, 2006) proposed a multistage method for a 3D segmentation of CT and MRI images and a new radial distance-based segmentation validation approach. Gu's algorithm is based on level sets and it incorporates an improved fast marching method and a morphological reconstruction model.…”

Novel Computational Approaches for Understanding Computed Tomography (CT) Images and Their Applications

“…Computers are indispensable for the analysis of large amounts of data, for tasks that require complex computation, or for the extraction of quantitative information. There are two important reasons for the use of computer aided segmentation: one is to improve upon the conventional expert (human)-based segmentation, and the other is to acquire segmentation prior to visualization or quantification for the analysis of medical images (Gu et al, 2006;Haris et al, 1998;Moga et al, 1998). The watershed transform is the method of choice and widely used for medical image segmentation.…”

“…We focus on a simpler ray tracing approach in this chapter to describe our X-ray imaging system. One of the important issues in medical imaging is to precisely segment structures of interest from a huge dataset, accurately represent them, efficiently visualize them, and perform measurements appropriate for diagnosis and therapy guidance, or other applications (Gu et al, 2006;Haris et al, 1998;Jos, 2001;Lagravere et al, 2008;Moga et al, 1998;Vincent, 1991). Advances in the area of computer science have a tremendous impact on the interpretation of medical images.…”

Bidirectional local distance measure for comparing segmentations

“…The distances should be mapped at each point on the reference surface and the distance should represent the distance to the test surface. Typical methods used in measuring the local distance differences from all points on a reference surface to a test surface are: the radial distance (RD) measure, [16][17][18] the normal (perpendicular) distance (ND) measure, 6,19 the minimum distance (MD) measure, 20, 21 and the ComGrad measure. 22 The radial distance is defined as the distance from the center of mass point (or line) of a segmentation to its surface per each radial direction.…”