Event Abstract

Back to Event

Segmentation and analysis of sub-cortical regions of autistic MR brain images using Gaussian distribution model based reaction diffusion multi-phase level sets and geometric feature

Jac Fredo A. R.1*, Kavitha G1 and Ramakrishnan S1
  • 1 Indian Institute of Technology Madras, Applied Mechanics, India

Autism is a neurodevelopmental disorder characterized by cognitive dysfunctions such as communication defects, poor social interactions and repetitive behaviours. It affects widely distributed cortical regions and shows extensive reduction in subcortical regions such as corpus callosum, brain stem and cerebellum. Magnetic resonance (MR) imaging is a non-invasive method, which provides information about the anatomy of sub-cortical regions. In the T1-weighted mid-sagittal MR brain images, corpus callosum has the appearance of broad arched band with bright pixel intensity. The brain stem and cerebellum appear as a mixture of white and gray pixels. In this work, the subcortical regions of control and autistic skull stripped MR brain images are segmented using Gaussian Distribution Model (GDM) based reaction diffusion multiphase level set method. The images considered for this analysis are obtained from autism brain imaging data exchange. In the multiphase level set, GDM is used as the intensity discriminator. The reaction diffusion is used to regularize the level set function. The curve is driven by a new Heaviside and Dirac functions to reach accurate boundaries. The level set function with two contours is used for the segmentation of sub-cortical regions. The results are validated with ground truth using Jaccard and Dice similarity measures. The geometric feature area is calculated from the cortical and subcortical regions. The results show that the GDM based reaction diffusion multiphase level set method is able to segment the regions. The level set method with two contours employed in this paper segments the brain into three regions. One of the contours in level set function extracts the high intensity pixels and the other extracts the low intensity pixels. From these images the desired sub-cortical regions such as corpus callosum, brain stem and cerebellum are labelled and separated from the undesired regions. The similarity measures calculated between segmented images and ground truth gives the values greater than 0.85. The geometric feature area calculated from the cortical and subcortical regions gives distinct variation (p<0.0001) between control and autistic images. As the geometric feature area extracted from cortical and sub-cortical regions are associated with brain dysfunction, this study helps to improve the diagnostic relevance of autistic subjects

Figure 1
Image
Figure 2
Image

Acknowledgements

The first author A. R. Jac Fredo is receiving fellowship from Maulana Azad National Fellowship for Minority students (F1-17.1/2011/MANF-CHR-TAM-1826) for his research work.

References

American Psychiatric Association, Diagnostic and statistical manual of mental disorders (2001) fifth edition, Washington DC,
Fahim, C., Meguid, N.A., Nashaat, N.H., Yoon, U., Mancini-Marie, A. and Evans, A. C. (2012) ‘The neuroanatomy of the autistic phenotype’, Research in Autism Spectrum Disorder, Vol. 6 No. 2 pp.898-906.
Prigge, M.B.D., Lange, N., Bigler, E.D., Merkleyg, T.L., Neeley, E.S., Abildskov, T.J., Froehlich, A.L., Nielsen, J.A., Cooperrider, J.R., Cariello, A.N., Ravichandran, C., Alexander, A.L. and Lainhart, J.E. (2013) ‘Corpus callosum area in children and adults with autism’, Research in Autism Spectrum Disorder, Vol. 7, No. 2, pp.221-234.
Webb, S.J., Sparks, B.F., Friedman, S.D., Shaw, D.W.W., Giedd, J., Dawson, G. and Dager, S.R. (2009) ‘Cerebellar vermal volumes and behavioral correlates in children with autism spectrum disorder’, Psychiatry Research, Vol. 172, No. 1, pp. 61-67.
Jou, R.J., Frazier, T.W., Keshavan, M.S., Minshewd, N.J. and Hardan A.Y. (2013) ‘A two-year longitudinal pilot MRI study of the brainstem in autism’, Behavioural Brain Research, Vol. 251, No. 15, pp. 163-167.
Elsayed, E., Coenen, F., Jiang, C., Garcia-Finana, M. and Sluming, V. (2010) ‘Corpus callosum MR image classification’, Knowledge Based System, Vol. 23, pp. 330-336.
Di Martino, A., Yan, C.G., Li, Q., Denio, E., Castellanos, F.X., Alaerts, K., Anderson, J.S., Assaf, M., Bookheimer, S.Y., Dapretto, M., Deen, B., Delmonte, S., Dinstein. I., Ertl-Wagner, B., Fair, D.A., Gallagher, L., Kennedy, D.P., Keown, C.L., Keysers, C., Lainhart, J.E., Lord, C., Luna, B., Menon, V., Minshew, N.J., Monk, C.S., Mueller, S., Müller, R.A., Nebel, M.B., Nigg, J.T., O'Hearn, K., Pelphrey, K.A., Peltier, S.J., Rudie, J.D., Sunaert, S., Thioux, M., Tyszka, J.M., Uddin, L.Q., Verhoeven, J.S., Wenderoth, N., Wiggins, J.L., Mostofsky, S.H., and Milham, M.P. (2013) ‘The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism’, Molecular Psychiatry, doi:10.1038/mp.2013.78
Wenchao, C.,Yi, W., Tao, L., Yangyu, F. and Yan, F. (2013) ‘Level set segmentation of medical images based on local region statistics and maximum a posteriori probability’, Computational and Mathematical Methods in Medicine, Vol. 2013, pp. 1-12.
Li, C., Huang, R., Ding, Z., Gatenby, J.C., Metaxas, D.N. and Gore, J.C. (2011) ‘A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI’, IEEE Transactions on Image Processing., Vol. 20, No. 7, pp. 2007-2016.
Yunjie, C., Jianwei, Z. and Jim Macione. (2009) ‘An improved level set method for brain MR images segmentation and bias correction’, Computerized Medical Imaging and Graphics, Vol. 33, pp. 510-519.
Kaihua, Z., Lei, Z., Huihui, S. and David, Z, (2012) ‘Re-initialization free level set evolution via reaction diffusion’, IEEE T Image Process, Vol. 22, pp. 258-271.

Keywords: Autistic, subcortical regions, multi-phase level set, Gaussian distribution model, reaction diffusion

Conference: Neuroinformatics 2014, Leiden, Netherlands, 25 Aug - 27 Aug, 2014.

Presentation Type: Poster, to be considered for oral presentation

Topic: Neuroimaging

Citation: A. R. J, G K and S R (2014). Segmentation and analysis of sub-cortical regions of autistic MR brain images using Gaussian distribution model based reaction diffusion multi-phase level sets and geometric feature. Front. Neuroinform. Conference Abstract: Neuroinformatics 2014. doi: 10.3389/conf.fninf.2014.18.00090

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: 28 Apr 2014; Published Online: 04 Jun 2014.

* Correspondence: Mr. Jac Fredo A. R., Indian Institute of Technology Madras, Applied Mechanics, Chennai, India, jack247029@gmail.com