The Use of Sieves to Stabilize Images Produced with the EM Algorithm for Emission Tomography

Images produced in emission tomography with the expectation-maximization (EM) algorithm have been observed to become more 'noisy' as the algorithm converges towards the maximum-likelihood estimate. We argue in this paper that there is an instability which is fundamental to maximum-likelihood estimation as it is usually applied and, therefore, is not a result of using the EM algorithm, which is but one numerical implementation for producing maximum-likelihood estimates. We show how Grenader's method of sieves can be used with the EM algorithm to remove the instability and thereby decrease the 'noise' artifact introduced into the images with little or no increase in computational complexity.

[1]  M. Miller,et al.  Maximum-Likelihood Reconstruction for Single-Photon Emission Computed-Tomography , 1985, IEEE Transactions on Nuclear Science.

[2]  Donald L. Snyder,et al.  Image Reconstruction from List-Mode Data in an Emission Tomography System Having Time-of-Flight Measurements , 1983, IEEE Transactions on Nuclear Science.

[3]  R. A. Gaskins,et al.  Nonparametric roughness penalties for probability densities , 2022 .

[4]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[5]  L. J. Thomas,et al.  A Matheematical Model for Positron-Emission Tomography Systems Having Time-of-Flight Measurements , 1981, IEEE Transactions on Nuclear Science.

[6]  Alan F. Karr,et al.  Maximum Likelihood Estimation in the Multiplicative Intensity Model via Sieves , 1987 .

[7]  R. Tapia,et al.  Nonparametric Probability Density Estimation , 1978 .

[8]  G. S. Watson.  Estimating the Intensity of a Poisson Process. , 1978 .

[9]  M. R. Leadbetter,et al.  On Estimation of Point Process Intensities. , 1982 .

[10]  L. Shepp,et al.  Maximum Likelihood Reconstruction for Emission Tomography , 1983, IEEE Transactions on Medical Imaging.

[11]  M E Raichle,et al.  Positron-emission tomography. , 1980, Scientific American.

[12]  G T Gullberg,et al.  Emission Computer Assisted Tomography with Single‐Photon and Positron Annihilation Photon Emitters , 1977, Journal of computer assisted tomography.

[13]  Michel M. Ter-Pogossian,et al.  Super PETT I: A Positron Emission Tomograph Utilizing Photon Time-of-Flight Information , 1982 .

[14]  R. Jaszczak,et al.  SPECT: Single Photon Emission Computed Tomography , 1980 .

[15]  R. Q. Edwards,et al.  Image Separation Radioisotope Scanning , 1963 .

[16]  I. Good.  Nonparametric roughness penalties for probability densities , 1971 .

[17]  M. Rosenblatt.  Remarks on Some Nonparametric Estimates of a Density Function , 1956 .

[18]  L. Shepp,et al.  Maximum Likelihood PET with Real Data , 1984, IEEE Transactions on Nuclear Science.

[19]  Stuart Geman,et al.  Sieves for Nonparametric Estimation of Densities and Regressions. , 1981 .

[20]  S. Geman,et al.  Nonparametric Maximum Likelihood Estimation by the Method of Sieves , 1982 .

[21]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .