TITLE:
Nonlinear Model of Image Noise: An Application on Computed Tomography including Beam Hardening and Image Processing Algorithms
AUTHORS:
Rafael Miller-Clemente, Marlen Perez Diaz, Larisa Zamora Matamoros, Sue Edyvean
KEYWORDS:
CT, Nonlinear Noise Model, Beam Hardening Effect, Image Processing Filters Effect
JOURNAL NAME:
Applied Mathematics,
Vol.5 No.8,
May
8,
2014
ABSTRACT:
This paper proposes a more inclusive
statistical model for predicting image noise in Computed Tomography (CT),
associated with scanning factors, considering the effect of beam hardening and
image processing filters. It is based on power functions where the levels of
the parameters will determine the rate of noise variation with respect to a
given scanning factor. It includes the influence of tube
potential, tube current, slice thickness, Field of View (FOV), reconstruction
methods and post-processing filters. To validate the model, tomographic
measurements were made by using a PMMA phantom that simulates paediatric head and adult abdomen, a PET
bottle was used to simulate the head of the new-born. The influence of ROI
(Region Of Interest) size over nonlinear model parameters was analysed, and
high variations of powers of attenuation and FOV were found depending on ROI
size. A nonlinear robust regression method was used. The validation was performed graphically by weighted residual
analysis. A nonlinear
noise model was obtained with an adjusted coefficient of determination for ROI sizes between 10% and 70% of the phantom diameter or FOV. The
model confirms the significance of the tube current, slice thickness and beam
hardening effect on image. The process of estimation of the parameters of the
model by Nonlinear Robust Regression turned out to be optimal.