Abstract
Nuclear Medicine (NM) images inherently suffer from large amounts of noise and
blur. The purpose of this research is to reduce the noise and blur while maintaining
image integrity for improved diagnosis. The proposal is to further improve image
quality after the standard pre- and post-processing undertaken by a gamma camera
system.
Mean Field Annealing (MFA), the image processing technique used in this research is
a well known image processing approach. The MFA algorithm uses two techniques
to achieve image restoration. Gradient descent is used as the minimisation technique,
while a deterministic approximation to Simulated Annealing (SA) is used for
optimisation. The algorithm anisotropically diffuses an image, iteratively smoothing
regions that are considered non-edges and still preserving edge integrity until
a global minimum is obtained. A known advantage of MFA is that it is able to
minimise to this global minimum, skipping over local minima while still providing
comparable results to SA with significantly less computational effort.
Image blur is measured using either a point or line source. Both allow for the
derivation of a Point Spread Function (PSF) that is used to de-blur the image. The
noise variance can be measured using a flood source. The noise is due to the random
fluctuations in the environment as well as other contributors. Noisy blurred
NM images can be difficult to diagnose particularly at regions with steep intensity
gradients and for this reason MFA is considered suitable for image restoration.
From the literature it is evident that MFA can be applied successfully to digital
phantom images providing improved performance over Wiener filters. In this paper
MFA is shown to yield image enhancement of planar NM images by implementing
a sharpening filter as a post MFA processing technique.
Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:wits/oai:wiredspace.wits.ac.za:10539/4498 |
Date | 29 February 2008 |
Creators | Falk, Daniyel Lennard |
Source Sets | South African National ETD Portal |
Language | English |
Detected Language | English |
Type | Thesis |
Format | 2307972 bytes, application/pdf, application/pdf |
Page generated in 0.0012 seconds