TOMOGRAPHIC IMAGE RECONSTRUCTION OF FAN-BEAM PROJECTIONS WITH EQUIDISTANT DETECTORS USING PARTIALLY CONNECTED NEURAL NETWORKS



Learning and Nonlinear Models - Revista da Sociedade Brasileira de Redes Neurais, Vol. 1, No. 2, pp. 122-130, 2003
© Sociedade Brasileira de Redes Neurais

For fan-beam geometry, the projections (in this case named p’) need to be multiplied by an adjust function, before the
filter [7]:

p ( n, θ) = p ' ( n, θ)    D

(21)


(22)


DD2 + n2

After the compensation, the convolution is carried out with a slight modification in the filter coefficients:

n=0

n even

n odd.


1

∕8,

h ( n ) = -0,

-1

The full reconstruction process consists on the two neural networks (filtering and backprojection) connected in
cascade. The output of filtering network is connected to the input of backprojection network. This can also be seen as a single
two-layer neural network and it could be implemented in an appropriate neural hardware.

3. Results

The proposed neural network was implemented in C++ and executed in a sequential processor for verification purposes. We
compared the times for reconstruction with and without interpolation (and fan-beam). The experiment was run on a
microcomputer with Pentium 1.6 MHz processor. The times were obtained from an average of 1000 algorithm runs. Table 1
lists the execution times for conventional backprojection algorithm and for neural network where the time to build the network
(calculate the weights) and the time to process the reconstruction were measured separately.

conventional
______________________________j_____________i__________________∙._____________________________________________________

partially connected neural network

parallel
-----

fan-beam
—----

parallel

fan-beam

build

run

build

run

no interpolation

293

512

250

57

524

57

with interpolation

369

707

347

108

656

108

Table 1 - Execution times (in milliseconds) for neural network and
conventional backprojection reconstruction of images with 100x100 pixels

Total time to reconstruct one image is greater for neural network but once the network has been assembled the time to
compute the reconstruction is very small. Network approach has noticeable advantages when several sections from an object
need to be reconstructed in sequence, like in a 3-D representation. For example, reconstruction of 10 slices by conventional
backprojection with fan-beam geometry would take 5.1s while the network would be constructed once and executed 10 times
in 1.1s, almost 5 times faster.


(α)                    (b)

Figure 8: Sheep-Logan phantom reconstructed with dimension 100x100 by neural network, (a) without interpolation and (b)
with interpolation.

In figure 8 reconstructed images without (a) and with (b) interpolation are shown. When interpolation is used a
smother image with less artifacts is achieved. To compare image quality we computed its peak signal to noise ratio (PSNR)
defined as the peak amplitude of the original phantom divided by the difference between original phantom and reconstructed
image expressed in dB. Figure 9 shows a plot of PSNR as a function of the number of (FIR) filter coefficients use in the

128



More intriguing information

1. Benchmarking Regional Innovation: A Comparison of Bavaria, Northern Ireland and the Republic of Ireland
2. Governance Control Mechanisms in Portuguese Agricultural Credit Cooperatives
3. Keystone sector methodology:network analysis comparative study
4. Spectral density bandwith choice and prewightening in the estimation of heteroskadasticity and autocorrelation consistent covariance matrices in panel data models
5. Modeling industrial location decisions in U.S. counties
6. An Attempt to 2
7. The name is absent
8. How Low Business Tax Rates Attract Multinational Headquarters: Municipality-Level Evidence from Germany
9. DEMAND FOR MEAT AND FISH PRODUCTS IN KOREA
10. Distribution of aggregate income in Portugal from 1995 to 2000 within a SAM (Social Accounting Matrix) framework. Modeling the household sector