A Novel Intelligent Wavelet Domain Noise Filtration Technique:Application to Medical Images

Abstract

Medical images, acquired with low exposure to radiation or after administering low-dose of imaging agents, often suffer due to noise arising from physiological sources and from acquisition hardware. The noise can be detrimental to the correct diagnosis as well for the computation of quantitative functional information. To overcome these deficiencies, this paper presents a genetic algorithm-based wavelet domain denoising technique. The proposed technique incorporates genetic algorithm within wavelet denoising framework for threshold optimization. The main purposes of the new technique are twofold: first, it intelligently adapts itself to various types of image noise without any prior knowledge of imaging process; secondly, it balances the preservation of diagnostic relevant details against the degree of noise reduction by optimizing the SNR and Liu’s error factor as the basis of objective function. The application of the new method on ultrasound and MR images of brain has shown a superior performance over the state-of-art wavelet-based denoising methods in terms of visual quality as well as quantitative metrics such as PSNR, RMSE and Liu’s error factor.