Order statistic-neural network hybrid filters for gamma camera-bremsstrahlung image restoration

An order statistic and neural network hybrid filter (OSNNH) is proposed for the restoration of gamma camera images using the measured modulation transfer function. Planar images of beta-emitting radionuclides are used to evaluate the filter because they exhibit higher degradation than images of single photon emitters due to increased photon scattering and collimator septal penetration. The filter performance is quantitatively evaluated and compared to that of the Wiener filter by investigating the relationship between the externally measured counts from sources of phosphorous-32 ((32)P) at various depths in water. An effective linear attenuation coefficient for (32)P is determined to be equal to 0.13 cm(-1) and 0.14 cm(-1) for the OSNNH and the Wiener filters, respectively. Evaluation of phantom and patient filtered images demonstrates that the OSNNH filter avoids ring effects caused by the ill-conditioned blur matrix and noise overriding caused by matrix inversion, typical of other restoration filters such as the Wiener.

[1]  B. C. Penney,et al.  A Wiener filter for nuclear medicine images. , 1983, Medical physics.

[2]  Wei Qian,et al.  A 3-D nonlinear recursive digital filter for video image processing , 1991, [1991] IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Conference Proceedings.

[3]  P W Doherty,et al.  Modifying constrained least-squares restoration for application to single photon emission computed tomography projection images. , 1988, Medical physics.

[4]  C B Saw,et al.  SPECT imaging of 131I (364 keV): importance of collimation , 1985, Nuclear medicine communications.

[5]  R. Chellappa,et al.  Image restoration with neural networks , 1992 .

[6]  B. K. Jenkins,et al.  Image restoration using a neural network , 1988, IEEE Trans. Acoust. Speech Signal Process..

[7]  M A King,et al.  Activity quantitation in SPECT: a study of prereconstruction Metz filtering and use of the scatter degradation factor. , 1991, Medical physics.

[8]  Alan C. Bovik,et al.  Theory of order statistic filters and their relationship to linear FIR filters , 1989, IEEE Trans. Acoust. Speech Signal Process..

[9]  Michael A. Fiddy,et al.  Superresolution algorithms for a modified Hopfield neural network , 1991, IEEE Trans. Signal Process..

[10]  Edward J. Coyle,et al.  Stack filters and neural networks , 1989, IEEE International Symposium on Circuits and Systems,.

[11]  D J Simpkin,et al.  The spatial and energy dependence of bremsstrahlung production about beta point sources in H2O. , 1992, Medical physics.

[12]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[13]  Alfredo Restrepo,et al.  Adaptive trimmed mean filters for image restoration , 1988, IEEE Trans. Acoust. Speech Signal Process..

[14]  Ronald J. Jaszczak,et al.  Physical Factors Affecting Quantitative Measurements Using Camera-Based Single Photon Emission Computed Tomography (Spect) , 1981, IEEE Transactions on Nuclear Science.

[15]  L P Clarke,et al.  Bremsstrahlung imaging using the gamma camera: factors affecting attenuation. , 1992, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[16]  Steve Webb.  The Mathematics of Image Formation and Image Processing , 1988 .

[17]  Michael A. King,et al.  Investigation of the stationarity of the modulation transfer function and the scatter fraction in conjugate view SPECT restoration filtering , 1989 .

[18]  G.L. Bilbro,et al.  Nonlinear adaptive filtering using annealed neural networks , 1990, IEEE International Symposium on Circuits and Systems.