| Summary: | Coded-aperture imaging offers a method of classical tomographic imaging by encoding the distance of a point from the detector by the lateral scale of the point response function. An estimate, termed a layergram, of the transverse sections of the object can be obtained by performing a simple correlation operation on the detector data. The estimate of one transverse plane contains artifacts contributed by source points from all other planes. These artifacts can be partially removed by a nonlinear algorithm which incorporates a priori knowledge of total integrated object activity per transverse plane, positivity of the quantity being measured, and lateral extent of the object in each plane. The algorithm is iterative and contains, at each step, a linear operation followed by the imposition of a constraint. The use of this class of algorithms is tested by simulating a coded-aperture imaging situation using a one-dimensional code and two-dimensional (one axis perpendicular to aperture) object. Results show nearly perfect reconstructions in noise-free cases for the codes tested. If finite detector resolution and Poisson source noise are taken into account, the reconstructions are still significantly improved relative to the layergram. The algorithm lends itself to implementation on an optical-digital hybrid computer. The problems inherent in a prototype device are characterized and results of its performance are presented.
|
|---|
