A powerful probabilistic model for noise analysis in medical images

Abstract

The statistical properties in various medical images demonstrate uncorrelated noise fluctuations. The signal noise fluctuations are generally due to physical imaging processes and have nothing to do with the tissue textures. Adding the noise types (e.g., quantization, electronics, photon) usually degrade medical images. The noise variation is usually assumed to be additive with zero-mean, constant variance Gaussian distribution. However, close consideration of different medical images indicates the need for better model representation to minimise the noise that can be vital in decision-making. This research proposed a probabilistic method to represent all real-type noise in general medical images. The method aims to cover most classical statistical models such as Gaussian, lognormal, Rayleigh, Weibull, and Nakagami without a prior examination to test for fitness. The proposed model was applied to actual clinical images to test the performance of the noise originating from the physical processes. The noise is assumed to be additive white Gaussian type with a zero mean and constant variance. The theoretical literature indicates that a nonlinear function can better represent noise. This research helps to form a relationship between the image intensity and the noise variance that yields the fitting parameters in the introduced nonlinear function. The validity of the proposed method was proved mathematically and tested using the well know Kolmogorov-Smirnov (K-S) and Akaike Information Criteria (AIC) tests. The method was successfully applied to various clinical images such as magnetic resonance, x-ray, and panoramic images. The model's performance is compared with the classical models using root mean squared error (RMSE), relative error (RE), and R 2 as the evaluation matrices. The presented model has outperformed all classic models.