Speeding up image reconstruction methods in coded mask gamma cameras usingneural networks: Application to the EM algorithm

When using gamma -ray coded-mask cameras, one does not get a direct image a s in classical optical cameras but the correlation of the mask response wit h the source. Therefore the data must be mathematically treated in order to reconstruct the original sky sources. Generally this reconstruction is bas ed on linear methods, such as correlating the detector plane with a reconst ruction array, or non-linear ones such as iterative or maximization methods (i.e. the EM algorithm). The latter have a better performance but they inc rease the computational complexity by taking a lot of time to reconstruct a n image. Here we present a method for speeding up such kind of algorithms b y making use of a neural network with a back-propagation learning rule.