Plenary lecture 1: on computational techniques based on nonlinear and fuzzy systems theory for NMR spectroscopy data mining
D.A. Karras · 2011
Magnetic resonance spectroscopic imaging (MRSI) integrates spectroscopic MRS and imaging methods to acquire spatially localized MRS spectra associated with a specific patient. MRSI is a relatively new imaging entity for clinical applications while MRS is a more widely used signal processing modality in clinical practice. Both are related to NMR spectroscopy and scanners. The goal of this plenary talk will be to present the computational techniques for processing such complex spectra towards efficient NMR data mining regarding potential applications in clinical practice. These techniques will be based on Nonlinear Signal Processing methodologies including Dynamical Systems Analysis and Global Optimization methods as well as on Fuzzy Systems Theory involving development of suitable 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 data mining in clinical applications.