MRI analysis of the spinal cord by snakes guided by the gradient vector flow (GVF)

Abstract

Event Abstract Back to Event MRI analysis of the spinal cord by snakes guided by the gradient vector flow (GVF) Assia CHERFA1* and Yazid CHERFA1 1 LARIM Laboratory, Saad Dahlab University, BLIDA, Algeria Problem Statement: In order to provide a semi-automatic aid diagnosis of some lesions and spinal cord injury, the aim of our work is to detect the edge of the human spinal cord or dural sac that surrounds it, from MR images of spinal cord sagittal plane, T2-weighted. After a step of pretreatments, we segment the spinal cord using snakes. Traditional snakes have major problems: - Difficulties to fit them into the concavities. - Difficulties in changing contours away from their current position - Difficulties in changing contours, if they cross the real contour To improve the deformation of the active contour, the external force replaces the traditional snake by a vector field. Approach: Before segmentation, we must apply a pretreatment phase, including: - Contrast Adjustment to enhance image quality, - A Gaussian filter to reduce noise, - A dilation followed by erosion to improve the contrast performance. This allows for better image quality and a separation between the two tissue-spinal and dural sac. The segmentation phase is to extract the contour of the area of interest from the preprocessed image, by a calculation of the field Gradient Vector (GVF) of this image. This flow must be standardized then obtain a new form of flow, noted “GVFN”', that guided our active contour during its deformation to the desired contour of the area of interest. During segmentation, we speak twice manually: once to select points on the dural sac and eliminate unwanted structures, a second to initialize the active contour. Results: The tests were performed on MR images showing the possibility of snakes guided by GVF to automatically manage the topology change of the curve still evolving. These tests show the good convergence of GVF snakes and guided by their strong progress towards the concavities. Conclusions/Recommendations: Snakes guided by GVF dependent initialization. It would be interesting to automate this segmentation process, eliminating two-step manual intervention. Keywords: Spinal Cord, Snakes, GVF, MRI, sci Conference: 4th Conference of the Mediterrarnean Neuroscience Society, Istanbul, Turkey, 30 Sep - 3 Oct, 2012. Presentation Type: Poster Presentation Topic: Abstracts Citation: CHERFA A and CHERFA Y (2013). MRI analysis of the spinal cord by snakes guided by the gradient vector flow (GVF). Conference Abstract: 4th Conference of the Mediterrarnean Neuroscience Society. doi: 10.3389/conf.fnhum.2013.210.00016 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 04 Apr 2013; Published Online: 11 Apr 2013. * Correspondence: Prof. Assia CHERFA, LARIM Laboratory, Saad Dahlab University, BLIDA, BLIDA, Algeria, assia_bz@yahoo.fr Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Assia CHERFA Yazid CHERFA Google Assia CHERFA Yazid CHERFA Google Scholar Assia CHERFA Yazid CHERFA PubMed Assia CHERFA Yazid CHERFA Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.