Convolutional micro-networks for MR-guided low dose PET post-processingDownload PDF

11 Apr 2018 (modified: 16 May 2018)MIDL 2018 Abstract SubmissionReaders: Everyone
  • Abstract: We propose a novel micro-network (mu-net) architecture which is a convolutional neural network (CNN) designed to be robust to minimal training data. Applying the mu-net to MR-guided low count PET scans produces impressive qualitative and quantitative cross-validation results despite training on just two noise realisations of the same patient.
  • Keywords: CNN, image processing, guided reconstruction, PET-MR
  • Author Affiliation: King's College London
3 Replies