Classification of brain SPECT imaging using 3D local multifractal spectrum for epilepsy detection

Abstract

Purpose Multifractal spectrum analysis is a discriminating tool that may distinguish volunteers and epileptic patients. In this study, our aim was to detect epileptogenic sources by computing the singularity spectrum. Materials and methods Multifractal analysis based on generalized concepts of fractals has been applied to evaluate biological tissues composed of complex structures. This analysis can provide a precise quantitative description for a broad range of heterogeneous phenomena. This study investigates the possibility of using a mathematical model (multifractal analysis) for image texture to detect the underlying source changes on SPECT images. Previously, reported on application of 3D multifractal analysis to describe the multifractal character of brain SPECT (Single-Photon Emission Computed Tomography) images and we showed that the multifractal spectrum is a discriminating tool to distinguish volunteers and epileptic patients. The experiment is divided into two phases. First, we developed a 3D method for the singularity spectrum compute. In the test phase, we applied this multifractal spectrum to the detection of epileptogenic sources in SPECT images. ResultsThe results obtained on a group of seven patients show that the proposed method is feasible and the results are encouraging. The epileptic fit sources obtained using the R. Lopes (B) · P. Dubois · N. Makni · N. Betrouni INSERM, U703, ITM, Pavillon Vancostenobel, system were in agreement with the opinion of expert diagnosticians. Conclusion Multifractal spectrum analysis provides a means of detecting and localizing epileptogenic foci in brain SPECT scans.

Identification of Structures in Medical Images

“…In order to capture the extraordinary morphological variability of the human brain, a number of automatic methods for identification and analysis of structures have been developed for different imaging modalities (Ashburner et al, 2003;Bandyopadhyay, 2011;Bresser et al, 2011;Ishii et al, 2009;Lopes et al, 2008;Ribbens et al, 2010;Rousset et al, 2007;Shiee et al, 2010;Tu & Bai, 2010;Yi et al, 2009;Zhang et al, 2011).…”