Motion in nuclear cardiology imaging: types, artifacts, detection and correction techniques

Abstract

In this paper, the authors review the field of motion detection and correction in nuclear cardiology with single photon emission computed tomography (SPECT) and positron emission tomography (PET) imaging systems. We start with a brief overview of nuclear cardiology applications and description of SPECT and PET imaging systems, then explaining the different types of motion and their related artefacts. Moreover, we classify and describe various techniques for motion detection and correction, discussing their potential advantages including reference to metrics and tasks, particularly towards improvements in image quality and diagnostic performance. In addition, we emphasize limitations encountered in different motion detection and correction methods that may challenge routine clinical applications and diagnostic performance.

Inverse radon transform with deep learning: an application in cardiac motion correction

“…However, to the extent we know deep learning has never been attempted before for cardiac MC embedded within the image reconstruction process, i.e. directly from the motion affected sinogram, or even as a post-processing after reconstruction (Mohammadi et al 2022) Our proposed approach of direct reconstruction of a motion-compensated image will eliminate the need for post-processing and significantly simplify the reconstruction process. We have also post-processed cardiac motion-blurred reconstructed images with U-net, which was not done before.…”