Unparalleled and revolutionary impact of PET imaging on research and day to day practice of medicine

Positron emission tomography (PET) imaging is the most quantitative modality for assessing disease activity at the molecular and cellular levels, and therefore, it allows monitoring its course and determining the efficacy of various therapeutic interventions. In this scientific communication, we describe the unparalleled and revolutionary impact of PET imaging on research and day to day practice of medicine. We emphasize the critical importance of the development and synthesis of novel radiotracers (starting from the enormous impact of F-Fluorodeouxyglucose (FDG) introduced by investigators at the University of Pennsylvania (PENN)) and PET instrumentation. These innovations have led to the total-body PET systems enabling dynamic and parametric molecular imaging of all organs in the body simultaneously. We also present our perspectives for future development of molecular imaging by multiphoton PET systems that will enable users to extract substantial information (owing to the evolving role of positronium imaging) about the related molecular and biological bases of various disorders, which are unachievable by the current PET imaging techniques.

Positron annihilation localization by nanoscale magnetization

In positron emission tomography (PET), the finite range over which positrons travel before annihilating with an electron places a fundamental physical limit on the spatial resolution of PET images. After annihilation, the photon pair detected by the PET instrumentation is emitted from a location that is different from the positron-emitting source, resulting in image blurring. Here, we report on the localization of positron range, and hence annihilation quanta, by strong nanoscale magnetization of superparamagnetic iron oxide nanoparticles (SPIONs) in PET-MRI. We found that positron annihilations localize within a region of interest by up to 60% more when SPIONs are present (with [Fe] = 3 mM) compared to when they are not. The resulting full width at half maximum of the PET scans showed the spatial resolution improved by up to $$\approx$$ ≈ 30%. We also found evidence suggesting that the radiolabeled SPIONs produced up to a six-fold increase in ortho-positronium. These results may also have implications for emerging cancer theranostic strategies, where charged particles are used as therapeutic as well as diagnostic agents and improved dose localization within a tumor is a determinant of better treatment outcomes.

Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy

This brief review summarizes the major applications of artificial intelligence (AI), in particular deep learning approaches, in molecular imaging and radiation therapy research. To this end, the applications of artificial intelligence in five generic fields of molecular imaging and radiation therapy, including PET instrumentation design, PET image reconstruction quantification and segmentation, image denoising (low-dose imaging), radiation dosimetry and computer-aided diagnosis, and outcome prediction are discussed. This review sets out to cover briefly the fundamental concepts of AI and deep learning followed by a presentation of seminal achievements and the challenges facing their adoption in clinical setting.