Motion correction of respiratory-gated PET images using deep learning based image registration framework.

CONCLUSIONS: In this work, we proposed a motion correction method for respiratory-gated PET images using deep learning based image registration framework. It does not require the knowledge of the true deformation field for training the network, which makes it very convenient to implement. We validated the proposed method using simulation and clinical data and showed its ability to reduce motion artifacts while utilizing all gated PET data.
PMID: 32244230 [PubMed - as supplied by publisher]

Source: Physics in Medicine and Biology - April 2, 2020 Category: Physics Authors: Li T, Zhang M, Qi W, Asma E, Qi J Tags: Phys Med Biol Source Type: research