Abstract
The widespread availability of high-performance computing and the popularity of artificial intelligence (AI) with machine learning and deep learning (ML/DL) algorithms at the helm have stimulated the development of many applications involving the use of AI-based techniques in molecular imaging research. Applications reported in the literature encompass various areas, including innovative design concepts in positron emission tomography (PET) instrumentation, quantitative image reconstruction and analysis techniques, computer-aided detection and diagnosis, as well as modeling and prediction of outcomes. This review reflects the tremendous interest in quantitative molecular imaging using ML/DL techniques during the past decade, ranging from the basic principles of ML/DL techniques to the various steps required for obtaining quantitatively accurate PET data, including algorithms used to denoise or correct for physical degrading factors as well as to quantify tracer uptake and metabolic tumor volume for treatment monitoring or radiation therapy treatment planning and response prediction.This review also addresses future opportunities and current challenges facing the adoption of ML/DL approaches and their role in multimodality imaging.
Highlights
Image analysis through the process of transfer learning
Similar attributes in natural images and medical images can contribute to the task of image segmentation or registration of molecular images. These tasks can be learned on the medical imaging domain with a smaller sample size by fine-tuning the algorithm to capture domain-specific salient features instead of learning the whole process from scratch. This capability is especially valuable in the case of molecular imaging, where information related to intensity differences, boundaries, edges, and possible textures is readily available from natural images and the DL/ML algorithms can focus on the salient features of physiological variations and tracer uptake distribution, for instance
These include solid-state technologies such as avalanche photodiodes (APDs) and, more recently, silicon photomultiplier tubes (SiPMs) operated in Geiger mode. Such magnetic resonance imaging (MRI)-compatible photodetectors can be operated within a magnetic field and as such are good candidates for building blocks of detector modules used in hybrid positron emission tomography (PET)/MRI systems. Owing to their numerous advantages compared with PMTs, SiPMs have been implemented in modern digital PET scanners, which are commercially available from major scanner manufacturers [17,18,19]
Summary
This is an exciting time for molecular imaging using PET technology, which is combined with either computed tomography (PET/CT) or magnetic resonance imaging (PET/MRI) to provide coregistered molecular and anatomical information. These include solid-state technologies such as avalanche photodiodes (APDs) and, more recently, silicon photomultiplier tubes (SiPMs) operated in Geiger mode Such MRI-compatible photodetectors can be operated within a magnetic field and as such are good candidates for building blocks of detector modules used in hybrid PET/MRI systems. Owing to their numerous advantages compared with PMTs, SiPMs have been implemented in modern digital PET scanners, which are commercially available from major scanner manufacturers [17,18,19].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
