Event Abstract Back to Event Automated segmentation of corpus callosum in MRI scans: application to tracking Alzheimer's disease progression Babak A. Ardekani1*, Sang Han Lee1 and Alvin H. Bachman1 1 The Nathan S. Klein Institute for Psychiatric Research, Medical Physics, United States Background: The mid-sagittal cross-section of the corpus callosum (CC) has been examined extensively using MRI in various pathologies including Alzheimer’s disease (AD). Hitherto, the majority of MRI studies of CC have used manual or semi-automatic tracings on a representative mid-sagittal slice. This approach is time-consuming, prone to errors, and expensive to carry out. Here, a fully automated mutli-atlas-based algorithm is presented for the segmentation of CC mid-sagittal cross-sectional area. The method is applied to healthy controls (HC) and AD patients in the Open Access Series of Brain Imaging Studies (OASIS) database. Methods: The mid-sagittal plane and the anterior and posterior commissures were detected automatically on 628 structural MRI scans. Using this information, a mid-sagittal slice was reconstructed and the CC was outlined manually on all scans. These data were used as atlases for automated segmentation using a novel mutli-atlas label fusion approach. The algorithm was then applied to 563 OASIS scans. The total mid-sagittal CC area (CCA), the CC circularity (CIR), and the CC thickness profile were measured and analyzed in relation to subjects’ sex, age, brain size, and AD diagnosis. Results: The algorithm was able to segment CC with a success rate of about 95%. Negative correlations were found between age and both CCA and CIR. There was a positive correlation between CCA and brain size, however, the CIR decreased with brain size. Controlling for age and brain size, CCA was larger and CIR was smaller in females. Controlling for age, sex, and brain size, CCA and CIR were both smaller in AD relative to HC. However, only CIR was significantly different between very mild and mild AD groups, being smaller in the latter. The rates of change of CCA and CIR were both significantly more negative in AD relative to HC. However, only the rate of change of CIR was different between very mild and mild AD, being more negative in the latter. Analysis of CC thickness profiles showed that the CC in AD is thinner that HC throughout the length of the CC but more significantly at the splenium and the genu. Discussion: This research offers a fast, robust, accurate, and fully automatic CC segmentation program (‘yuki’) available publicly (www.nitrc.org/projects/art). We confirmed the hotly debated existence of a sexual dimorphism in CC size and shape. We showed the circularity of the CC to be a more effective measure than its size for tracking AD progression. Keywords: MRI, Corpus Callosum, image segmentation, Alzheimer’s disease, Sex Conference: ACNS-2013 Australasian Cognitive Neuroscience Society Conference, Clayton, Melbourne, Australia, 28 Nov - 1 Dec, 2013. Presentation Type: Poster Topic: Other Citation: Ardekani BA, Lee S and Bachman AH (2013). Automated segmentation of corpus callosum in MRI scans: application to tracking Alzheimer's disease progression. Conference Abstract: ACNS-2013 Australasian Cognitive Neuroscience Society Conference. doi: 10.3389/conf.fnhum.2013.212.00057 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: 15 Oct 2013; Published Online: 25 Nov 2013. * Correspondence: Dr. Babak A Ardekani, The Nathan S. Klein Institute for Psychiatric Research, Medical Physics, New York, New York, 12518, United States, Ardekani@nki.rfmh.org 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 Babak A Ardekani Sang Han Lee Alvin H Bachman Google Babak A Ardekani Sang Han Lee Alvin H Bachman Google Scholar Babak A Ardekani Sang Han Lee Alvin H Bachman PubMed Babak A Ardekani Sang Han Lee Alvin H Bachman 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.
Read full abstract