Development of an Ideal Observer that Incorporates Nuisance Parameters and Processes List-Mode Data
This work addresses radiation imaging for plutonium inspection in arms control, representing an incremental improvement in observer models for a specific domain.
The researchers tackled the problem of binary discrimination tasks in arms-control-treaty contexts by developing an ideal observer model that processes list-mode data and incorporates nuisance parameters like object orientation and count-rate variability, resulting in superior performance as measured by the area under the receiver operating characteristic curve.
Observer models were developed to process data in list-mode format in order to perform binary discrimination tasks for use in an arms-control-treaty context. Data used in this study was generated using GEANT4 Monte Carlo simulations for photons using custom models of plutonium inspection objects and a radiation imaging system. Observer model performance was evaluated and presented using the area under the receiver operating characteristic curve. The ideal observer was studied under both signal-known-exactly conditions and in the presence of unknowns such as object orientation and absolute count-rate variability; when these additional sources of randomness were present, their incorporation into the observer yielded superior performance.