DeepPET: A deep encoder–decoder network for directly solving the PET image reconstruction inverse problem

•Positron Emission Tomography (PET) has become a key imaging method in cancer care.•DeepPET is a deep neural network to reconstruct images directly from PET sinograms.•Reconstruction speed is 108 times faster compared to conventional techniques.•Image quality is improved over conventional techniques...

Full description

Saved in:

Bibliographic Details
Published in:	Medical image analysis Vol. 54; pp. 253 - 262
Main Authors:	Häggström, Ida, Schmidtlein, C. Ross, Campanella, Gabriele, Fuchs, Thomas J.
Format:	Journal Article
Language:	English
Published:	Netherlands Elsevier B.V 01.05.2019 Elsevier BV
Subjects:	Algorithms Computer applications Computer simulation Deep Learning Digital imaging Humans Image acquisition Image Enhancement - methods Image processing Image Processing, Computer-Assisted - methods Image quality Image reconstruction Inverse problems Machine learning Neural Networks, Computer Noise levels Optimization Positron emission Positron emission tomography Signal to noise ratio Tomography
ISSN:	1361-8415, 1361-8423, 1361-8423
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!