Automatic Intracranial Space Segmentation for Computed Tomography Brain Images
- PDF / 399,117 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 100 Downloads / 231 Views
Automatic Intracranial Space Segmentation for Computed Tomography Brain Images C. Adamson & A. C. Da Costa & R. Beare & A. G. Wood
Published online: 6 November 2012 # Society for Imaging Informatics in Medicine 2012
Abstract Craniofacial disorders are routinely diagnosed using computed tomography imaging. Corrective surgery is often performed early in life to restore the skull to a more normal shape. In order to quantitatively assess the shape change due to surgery, we present an automated method for intracranial space segmentation. The method utilizes a twostage approach which firstly initializes the segmentation with a cascade of mathematical morphology operations. This segmentation is then refined with a level-set-based approach that ensures that low-contrast boundaries, where bone is absent, are completed smoothly. We demonstrate this method on a dataset of 43 images and show that the method produces consistent and accurate results.
C. Adamson : R. Beare : A. G. Wood Developmental Imaging, Murdoch Childrens Research Institute, Parkville, Melbourne, Australia A. C. Da Costa Department of Plastic and Maxillofacial Surgery, The Royal Children’s Hospital, Melbourne, Australia A. C. Da Costa : A. G. Wood Australian Centre for Child Neuropsychology Studies, Murdoch Childrens Research Institute, Melbourne, Australia R. Beare : A. G. Wood Department of Medicine, Southern Clinical School, Monash University, Melbourne, Australia A. G. Wood (*) School of Psychology, University of Birmingham, Edgbaston, Birmingham B15 2TT, UK e-mail: [email protected]
Keywords Intracranial space segmentation . Computed tomography . Level set methods . Mathematical morphology
Introduction Given its high contrast-to-noise ratio for bone and soft tissue, computed tomography (CT) imaging is routinely used as a diagnostic tool for craniofacial disorders. Craniofacial disorders, one of the most common being craniosynostosis, are a group of deformities in the growth patterns of the skull and facial bones, which are reflected in the abnormal geometry of the intracranial space (ICS). A preoperative scan is commonly acquired for diagnostic purposes. A postoperative imaging may be performed in order to assess the efficacy of the surgical technique in restoring a more normal ICS shape. In order to quantitatively evaluate changes in shape, a segmentation method for CT images is required. An accurate ICS segmentation is also useful for measuring intracranial volume. The ICS is defined as the volume enclosed by the frontal, occipital, sphenoid and ethmoid bones, and two each of the parietal and temporal bones of the skull [1]. Figure 1a shows an example brain CT image with the ICS boundary shown in orthogonal planes. The challenging part of ICS segmentation is that the ICS is not enclosed by a continuous, highcontrast border due to features such as the fontanelles and the foramen magnum (see Fig. 1b). Ideally, an ICS segmentation method would smoothly interpolate over boundary segments with no or little contrast. Intracranial image segmentation tech
Data Loading...
