PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Dual-tracer PET signal separation is a typical problem in the field of PET imaging. Previous studies mainly focused on separating dual-tracer PET signals on activity image reconstructed by traditional iterative methods, which ignore the influence of quality of reconstructed images and need additional time for reconstruction pro- cedure. In this work, dual-tracer PET signal separation is cracked as simultaneously direct reconstruction and separation from mixed sinogram based on deep learning, we introduced a three-dimensional encoder-decoder net- work to achieve it. The network can learn and combine temporal information and spatial information properly, and spatiotemporal information plays an important role in signal separation and structure reconstruction respec- tively. We evaluated the proposed method both in Monte Carlo simulation experiment and SD rats experiment. Experimental results show that the proposed method can obtain better single tracer PET activity image than another method also based on deep learning and belongs to direct reconstruction.
Fuzhen Zeng andHuafeng Liu
"Dual-tracer PET image direct reconstruction and separation based on three-dimensional encoder-decoder network", Proc. SPIE 11553, Optics in Health Care and Biomedical Optics X, 115530X (10 October 2020); https://doi.org/10.1117/12.2573439
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Fuzhen Zeng, Huafeng Liu, "Dual-tracer PET image direct reconstruction and separation based on three-dimensional encoder-decoder network," Proc. SPIE 11553, Optics in Health Care and Biomedical Optics X, 115530X (10 October 2020); https://doi.org/10.1117/12.2573439