Adaptive Fuzzy Control Approach for Enhancement of Electron Magnetic Resonance Tomograms

Electron magnetic resonance imaging (EMRI), a technique akin to MRI, is fast emerging as a functional imaging modality. But, the poor SNR, originating from the low frequency operation of the EMRI scanner as well as the toxicity-limited dose of the exogenously administrated imaging agents, has hindered the development of EMRI to a viable biomedical technology. Hence novel image enhancement techniques are in need to enhance the potential of EMRI. In this paper, we propose one such system based on a fuzzy control filtering approach, using adaptively varying membership functions and incorporating fuzzy associative memory (FAM) with conventional multilevel median filter (MLMF). The performance of the system is tested using in vivo EMR images, acquired from a continuous wave (CW) radio frequency (RF) EMR imager and is evaluated visually as well as by computing quantitative metrics such as root mean square error (RMSE) and peak signal to noise ratio (PSNR). Visual and quantitative evaluation show fuzzy filters, especially the one with a new parabolic membership function, to outperform the conventional MLMF method.