This project aims to automatically recover and analyze the 3D hippocampal shape from human brain MRI and localize the epileptic focus to the appropriate temporal lobe. The hypothesis is that shape differences (not volume) between the left and right hippocampi will distinguish patients with epilepsy from healthy controls and identify the hemispheric location of the epileptic focus. We propose a three phase solution to test this hypothesis: (a) the development of a learning algorithm to create hippocampal shape and image atlases for use in segmentation, (b) automatic (atlas-based) hippocampal segmentation and validation, and (c) automatic classification of patient scans and validation of the classifier. The proposed new segmentation scheme will involve an atlas-based approach wherein the atlas is constructed from a prospective data set using a novel learning algorithm based on finding the atlas shape as the minimum distance fitted shape from the given population of fitted shapes. An MR image atlas learned similarly will be used to augment the learned shape prior. The learnt atlases will then be employed for estimating the non-rigid deformation field required to achieve an atlas-based segmentation of the unknown subject scan from an archive of retrospective data. A novel classifier based on the Kernel Fischer discriminant is proposed for automatically classifying subjects into groups corresponding to controls and those with epileptic foci localized to either the left or the right lobe. The segmentation and the classification algorithms will be validated on synthetic and real MR brain scans from an archive. The proposed algorithmic schemes have considerable potential for use in the segmentation and analysis of other anatomical structures and thus have utility for other disease states.
| Kim, Hyunwoo J; Adluru, Nagesh; Banerjee, Monami et al. (2015) Interpolation on the manifold of K component GMMs. Proc IEEE Int Conf Comput Vis 2015:2884-2892 |
| Chen, Ting; Vemuri, Baba C; Rangarajan, Anand et al. (2011) Mixture of segmenters with discriminative spatial regularization and sparse weight selection. Med Image Comput Comput Assist Interv 14:595-602 |
| Chen, Ting; Vemuri, Baba C; Rangarajan, Anand et al. (2010) Group-wise Point-set registration using a novel CDF-based Havrda-Charvát Divergence. Int J Comput Vis 86:111-124 |
| Xie, Yuchen; Ho, Jeffrey; Vemuri, Baba C (2010) Image Atlas Construction via Intrinsic Averaging on the Manifold of Images. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2010:2933-2939 |
| Chen, Ting; Rangarajan, Anand; Vemuri, Baba C (2010) CAVIAR: CLASSIFICATION VIA AGGREGATED REGRESSION AND ITS APPLICATION IN CLASSIFYING OASIS BRAIN DATABASE. Proc IEEE Int Symp Biomed Imaging 2010:1337-1340 |
| Liu, Meizhu; Vemuri, Baba C; Amari, Shun-Ichi et al. (2010) Total Bregman Divergence and its Applications to Shape Retrieval. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit :3463-3468 |
| Chen, Ting; Rangarajan, Anand; Eisenschenk, Stephan J et al. (2010) Construction of neuroanatomical shape complex atlas from 3D brain MRI. Med Image Comput Comput Assist Interv 13:65-72 |
| Seo, Dohyung; Vemuri, Baba C (2009) Complex Diffusion on Scalar and Vector Valued Image Graphs. Lect Notes Comput Sci 5681:98-111 |
| Rajwade, Ajit; Banerjee, Arunava; Rangarajan, Anand (2009) Probability density estimation using isocontours and isosurfaces: applications to information-theoretic image registration. IEEE Trans Pattern Anal Mach Intell 31:475-91 |
| Wang, Fei; Vemuri, Baba; Syeda-Mahmood, Tanveer (2009) Generalized L2-divergence and its application to shape alignment. Inf Process Med Imaging 21:227-38 |
Showing the most recent 10 out of 24 publications
