2010 | OriginalPaper | Buchkapitel
A Statistical Appraoch to Image Reconstruction from Projections Problem Using Recurrent Neural Network
verfasst von : Robert Cierniak
Erschienen in: Artificial Neural Networks – ICANN 2010
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper is concerned with the image reconstruction from projections problem. The presented paper describes a reconstruction approach based on recurrent neural network. The structure of this network is designed taking into account the probabilistic nature of distortion obesrved in x-ray computed tomography. The reconstruction process is performed using in this way constructed neural network solving the optimization problem. Computer experiments show that the appropriately designed recurrent neural network is able to reconstruct an image with better quality in comparison to the standart analytical reconstruction algorithm.