A computional intelligence framework for NMR spectroscopy imaging and retrieval

Summary form only given. Magnetic resonance spectroscopic imaging (MRSI) combines quantitation of MRS signals and imaging algorithms in order to obtain spatially localized MRS spectra corresponding to a unique clinical subject. MRSI is a relatively new imaging modality for clinical applications compared to MRS spectroscopy quantitation methodologies. Both are related to NMR scanners and spectroscopy. The goal of this plenary talk will be to present a computational intelligent framework for processing such complex spectra modalities towards designing an efficient CBIR system for NMR potential clinical applications. These methodologies will be based on Nonlinear Signal Processing techniques including Dynamical Systems Analysis, Global Optimization methods including Genetic Algorithms as well as on Fuzzy Systems Theory involving development and evaluation of suitable complex Fuzzy Descriptors. A series of experiments illustrate the feasibility and potential of the proposed approaches using synthetic images and model MRS signals derived from benchmark MRS spectra, towards successful NMR spectra retrieval in clinical applications.