USE OF THE EM ALGORITHM FOR MAXIMUM-LIKELIHOOD-ESTIMATION IN ELECTRON-MICROSCOPE AUTORADIOGRAPHY

In this paper we describe a new method for the analysis of electron mi croscope autoradiographs. It uses a Poisson model to describe the auto radiographic grain distribution, and the method of maximum likelihood to estimate the radioactive intensities. An iterative procedure is der ived from the EM algorithm to produce maximum likelihood estimates. Th e procedure leads to simple iterative calculations and a complete trea tment of edge effects. The resulting method of analysis enables data f rom the whole area of autoradiograph plates to be utilized without the need for any form of windowing to guard against edge effects. It also facilitates inference about the precision of estimated intensities an d about comparisons between intensities. The estimation procedures are illustrated with real autoradiograph data from a study of rabbit bloo d plasma.