In Maximum Entropy and Bayesian Methods, A. Mohammad-Djafari and G. Demoment, eds., pp. 415-421 (Kluwer Academic, Dordrecht, 1993)

Binary task performance on images reconstructed using MEMSYS 3: Comparison of machine and human observers

Kyle J. Myers and Robert F. Wagner
Center for Devices and Radiological Health, FDA Kenneth M. Hanson
Los Alamos National Laboratory


We have previously described how imaging systems and image reconstruction algorithms can be evaluated on the basis of how well binary-discrimination tasks can be performed by a machine algorithm that “views” the reconstructions. The present work examines the performance of a family of algorithmic observers viewing tomographic images reconstructed using the Cambridge Maximum Entropy software, MEMSYS 3. We investigate the effects on the performance of these observers due to varying the parameter alpha, which controls the strength of the prior in the iterative reconstruction technique. Measurements on human observers performing the same task show that they perform comparably to the best machine observers in the region of highest machine scores, i.e., smallest values of alpha. For increasing values of alpha, both human and machine observer performance degrade. The falloff in human performance is more rapid than that of the machine observer, a behavior common to all such studies of the so-called psychometric function.

Keywords: human observer, machine observer, MEMSYS, maximum-entropy reconstruction, binary discrimination task, tomographic reconstruction, psychometric function

Get full paper (pdf, 2008 KB)
Return to publication list
Send e-mail to author at