Scientific article
Open access

The promise of artificial intelligence and deep learning in PET and SPECT imaging

Published inPhysica Medica, vol. 83, p. 122-137
Publication date2021

This review sets out to discuss the foremost applications of artificial intelligence (AI), particularly deep learning (DL) algorithms, in single-photon emission computed tomography (SPECT) and positron emission tomography (PET) imaging. To this end, the underlying limitations/challenges of these imaging modalities are briefly discussed followed by a description of AI-based solutions proposed to address these challenges. This review will focus on mainstream generic fields, including instrumentation, image acquisition/formation, image reconstruction and low-dose/fast scanning, quantitative imaging, image interpretation (computer-aided detection/diagnosis/prognosis), as well as internal radiation dosimetry. A brief description of deep learning algorithms and the fundamental architectures used for these applications is also provided. Finally, the challenges, opportunities, and barriers to full-scale validation and adoption of AI-based solutions for improvement of image quality and quantitative accuracy of PET and SPECT images in the clinic are discussed.

  • Artificial intelligence
  • Deep learning
  • Molecular imaging
  • PET
  • Swiss National Science Foundation - SNRF 320030_176052
  • Autre - Fondation privée des HUG RC-06-01
Citation (ISO format)
ARABI, Hossein et al. The promise of artificial intelligence and deep learning in PET and SPECT imaging. In: Physica Medica, 2021, vol. 83, p. 122–137. doi: 10.1016/j.ejmp.2021.03.008
Main files (1)
Article (Published version)
ISSN of the journal1120-1797

Technical informations

Creation03/23/2021 12:56:00 PM
First validation03/23/2021 12:56:00 PM
Update time03/16/2023 12:38:08 AM
Status update03/16/2023 12:38:08 AM
Last indexation02/12/2024 1:26:42 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack