SPHARM-Based Shape Analysis of Hippocampus for Lateralization in Mesial Temporal Lobe Epilepsy Mohammad Esmaeil-Zadeh Control and Intelligent Processing Centre of Excellence (CIPCE), School of Electrical and Computer Engineering University of Tehran Tehran 14395-515, Iran m.esmaeilzadeh@ut.ac.ir Hamid Soltanian-Zadeh CIPCE, University of Tehran Tehran 14395-515, Iran & Henry Ford Hospital Detroit, MI 48202, USA hszadeh@ut.ac.ir, hamids@rad.hfh.edu Kourosh Jafari-Khouzani Department of Diagnostic Radiology Henry Ford Hospital Detroit, MI 48202, USA kjafari@rad.hfh.edu Abstract— Spherical harmonics (SPHARM) is a powerful tool for modelling and processing of 3D connected objects of any shape. SPHARM popularity lies in its capability of revealing surfaces global discrepancies in a multi-scale manner. In medical image analysis, this capability is of great importance in diagnosis of diseases that are related to deformations in the brain structures, such as mesial temporal lobe epilepsy that is associated with the hippocampus deformation. In this paper, we present a simple and practical method for SPHARM registration, which is required for conducting shape comparisons. The method utilizes concepts of principal components and solves the challenging problem of SPHARM registration. Our method benefits from characteristics of SPHARM coefficients that have independent [x,y,z] elements; so registration is easily performed in the SPHARM feature space. Then, we propose our feature selection methods that summarize 1536 SPHARM-based features of each subject into three lateralization indices. These three indices measure the distances between left and right hippocampi of healthy and epileptic subjects to detect the epileptogenic hippocampus. This work improves the lateralization accuracy from 78% of conventional volumetric method to 85%, and also in cases where volumetric analysis is uncertain, 16% improvement is achieved. This method could be used as a compliment to other methods to decrease lateralization error. Keywords-magnetic resonance imaging (MRI); hippocampus shape analysis; mesial temporal lobe epilepsy (mTLE); spherical harmonics; 3D representation and registration I. INTRODUCTION Shape analysis of brain structures has achieved great importance in the context of medical image computing in the recent years. The importance of neurodegenerative disorders (such as Alzheimer's, Schizophrenia, Parkinson and Epilepsy) and also evidences that show relations between these diseases and deformation of the brain structures [1-3] have increased research in this field. Hippocampus (HC) is a brain structure that belongs to the limbic system and is located in the medial temporal lobe. It plays important roles in the short-term memory, the formation of memories and language tasks [4]. In the above mentioned disorders, HC is usually vulnerable to damage at the very earliest stages and is the main target of deformation. So as a biomarker, accurate and timely morphologic assessment of this structure may be beneficial in prognosis and diagnosis of those diseases. In mesial temporal lobe epilepsy (mTLE), lateralization is referred to finding of the epileptogenic side, which is frequently associated with the hippocampus. This is critical for hippocampal resection, a surgical solution for patients with refractory epilepsy. Hippocampal volumetry along with some other MRI measures are the conventional methods for such assessment. Although volumetry is capable of revealing major deformations and global differences in some disorders [5], it is blind to minuscule shape changes. So in order to better compare the HCs, researches have focused on quantitative shape analysis methods with better discriminant features. Some researchers have proposed to apply deformable registration to a template [1,6,7]. Despite problems of template selection and high dimensionality of transformation, these studies achieved reasonable results. The methods in [8,9] were among the first methods proposed for 3D shape analysis based on sampled descriptions. Cootes, et al. [10] proposed Point Distribution Model for 3D shape analysis and deformation study. Other shape analysis methods based on medial shape descriptions in 3D and 2D were proposed by Styner [11] and Golland [12], respectively. Besides these, some methods build a simplified representation of anatomical structure by utilizing shape descriptors, such as spherical harmonics (SPHARM) [13], spherical wavelets [14], and Laplace-Beltrami operator [15]. In these methods, shape or surface is decomposed into series of bases and the coefficients are used as descriptive features. Proceedings of ICEE 2010, May 11-13, 2010 978-1-4244-6760-0/10/$26.00 ©2010 IEEE