Potential Applications of Artificial Intelligence and Machine Learning in Radiochemistry and Radiochemical Engineering

Light-Driven Radiochemistry with Fluorine-18, Carbon-11 and Zirconium-89

This review discusses recent advances in light-driven radiochemistry for three key isotopes: fluorine-18, carbon-11, and zirconium-89, and their applications in positron emission tomography (PET). In the case of fluorine-18, the predominant approach involves the use of cyclotron-produced [18F]fluoride or reagents derived thereof. Light serves to activate either the substrate or the fluorine-18 labeled reagent. Advancements in carbon-11 photo-mediated radiochemistry have been leveraged for the radiolabeling of small molecules, achieving various transformations, including 11C-methylation, 11C-carboxylation, 11C-carbonylation, and 11C-cyanation. Contrastingly, zirconium-89 photo-mediated radiochemistry differs from fluorine-18 and carbon-11 approaches. In these cases, light facilitates a postlabeling click reaction, which has proven valuable for the labeling of large biomolecules such as monoclonal antibodies (mAbs). New technological developments, such as the incorporation of photoreactors in commercial radiosynthesizers, illustrate the commitment the field is making in embracing photochemistry. Taken together, these advances in photo-mediated radiochemistry enable radiochemists to apply new retrosynthetic strategies in accessing novel PET radiotracers.

Radiochemistry: A Hot Field with Opportunities for Cool Chemistry

Recent Food and Drug Administration (FDA) approval of diagnostic and therapeutic radiopharmaceuticals and concurrent miniaturization of particle accelerators leading to improved access has fueled interest in the development of chemical transformations suitable for short-lived radioactive isotopes on the tracer scale. This recent renaissance of radiochemistry is paired with new opportunities to study fundamental chemical behavior and reactivity of elements to improve their production, separation, and incorporation into bioactive molecules to generate new radiopharmaceuticals. This outlook outlines pertinent challenges in the field of radiochemistry and indicates areas of opportunity for chemical discovery and development, including those of clinically established (C-11, F-18) and experimental radionuclides in preclinical development across the periodic table.

Proceedings of international symposium of trends in radiopharmaceuticals 2023 (ISTR-2023)

The International Atomic Energy Agency (IAEA) held the 3rd International Symposium on Trends in Radiopharmaceuticals, (ISTR-2023) at IAEA Headquarters in Vienna, Austria, during the week of 16-21 April 2023. This procedural paper summarizes highlights from symposium presentations, posters, panel discussions and satellite meetings, and provides additional resources that may be useful to researchers working with diagnostic and therapeutic radiopharmaceuticals in the academic, government and industry setting amongst IAEA Member States and beyond. More than 550 participants in person from 88 Member States attended the ISTR-2023. Over 360 abstracts were presented from all over the world by a diverse group of global scientists working with radiopharmaceuticals. Given this group of international radiochemists is unique to ISTR (IAEA funding enabled many to attend), there was an invaluable wealth of knowledge on the global state of the radiopharmaceutical sciences present at the meeting. The intent of this Proceedings paper is to share this snapshot from our international colleagues with the broader radiopharmaceutical sciences community by highlighting presentations from the conference on the following topics: Isotope Production and Radiochemistry, Industrial Insights, Regional Trends, Training and Education, Women in the Radiopharmaceutical Sciences, and Future Perspectives and New Initiatives. The authors of this paper are employees of IAEA, members of the ISTR-2023 Organizing Committee and/or members of the EJNMMI Radiopharmacy and Chemistry Editorial Board who attended ISTR-2023. Overall, ISTR-2023 fostered the successful exchange of scientific ideas around every aspect of the radiopharmaceutical sciences. It was well attended by a diverse mix of radiopharmaceutical scientists from all over the world, and the oral and poster presentations provided a valuable update on the current state-of-the-art of the field amongst IAEA Member States. Presentations as well as networking amongst the attendees resulted in extensive knowledge transfer amongst the various stakeholders representing 88 IAEA Member States. This was considered particularly valuable for attendees from Member States where nuclear medicine and the radiopharmaceutical sciences are still relatively new. Since the goal is for the symposium series to be held every four years; the next one is anticipated to take place in 2027.

The Development and Validation of Radiopharmaceuticals Targeting Bacterial Infection

The International Atomic Energy Agency organized a technical meeting at its headquarters in Vienna, Austria, in 2022 that included 17 experts representing 12 countries, whose research spanned the development and use of radiolabeled agents for imaging infection. The meeting focused largely on bacterial pathogens. The group discussed and evaluated the advantages and disadvantages of several radiopharmaceuticals, as well as the science driving various imaging approaches. The main objective was to understand why few infection-targeted radiotracers are used in clinical practice despite the urgent need to better characterize bacterial infections. This article summarizes the resulting consensus, at least among the included scientists and countries, on the current status of radiopharmaceutical development for infection imaging. Also included are opinions and recommendations regarding current research standards in this area. This and future International Atomic Energy Agency-sponsored collaborations will advance the goal of providing the medical community with innovative, practical tools for the specific image-based diagnosis of infection.

Accelerating radiochemistry development: Automated robotic platform for performing up to 64 droplet radiochemical reactions in a morning

The growing discovery and development of novel radiopharmaceuticals and radiolabeling methods requires an increasing capacity for radiochemistry experiments. However, such studies typically rely on radiosynthesizers designed for clinical batch production rather than research, greatly limiting throughput. Two general solutions are being pursued to address this: developing new synthesis optimization algorithms to minimize how many experiments are needed, and developing apparatus with enhanced experiment throughput. We describe here a novel high-throughput system based on performing arrays of droplet-based reactions at 10 μL volume scale in parallel. The automatic robotic platform can perform a set of 64 experiments in ~3 h (from isotope loading to crude product, plus sampling onto TLC plates), plus ~1 h for off-line radio-TLC analysis and radioactivity measurements, rather than the weeks or months that would be needed using a conventional system. We show the high repeatability and low crosstalk of the platform and demonstrate optimization studies for two 18F-labeled tracers. This novel automated platform greatly increases the practicality of performing arrays of droplet reactions by eliminating human error, vastly reducing tedium and fatigue, minimizing radiation exposure, and freeing up radiochemist time for other intellectually valuable pursuits.

Artificial Intelligence in Nuclear Medicine: Opportunities, Challenges, and Responsibilities Toward a Trustworthy Ecosystem

Trustworthiness is a core tenet of medicine. The patient-physician relationship is evolving from a dyad to a broader ecosystem of health care. With the emergence of artificial intelligence (AI) in medicine, the elements of trust must be revisited. We envision a road map for the establishment of trustworthy AI ecosystems in nuclear medicine. In this report, AI is contextualized in the history of technologic revolutions. Opportunities for AI applications in nuclear medicine related to diagnosis, therapy, and workflow efficiency, as well as emerging challenges and critical responsibilities, are discussed. Establishing and maintaining leadership in AI require a concerted effort to promote the rational and safe deployment of this innovative technology by engaging patients, nuclear medicine physicians, scientists, technologists, and referring providers, among other stakeholders, while protecting our patients and society. This strategic plan was prepared by the AI task force of the Society of Nuclear Medicine and Molecular Imaging.

In Silico Approaches for Addressing Challenges in CNS Radiopharmaceutical Design

Positron emission tomography (PET) is a highly sensitive and versatile molecular imaging modality that leverages radiolabeled molecules, known as radiotracers, to interrogate biochemical processes such as metabolism, enzymatic activity, and receptor expression. The ability to probe specific molecular and cellular events longitudinally in a noninvasive manner makes PET imaging a particularly powerful technique for studying the central nervous system (CNS) in both health and disease. Unfortunately, developing and translating a single CNS PET tracer for clinical use is typically an extremely resource-intensive endeavor, often requiring synthesis and evaluation of numerous candidate molecules. While existing in vitro methods are beginning to address the challenge of derisking molecules prior to costly in vivo PET studies, most require a significant investment of resources and possess substantial limitations. In the context of CNS drug development, significant time and resources have been invested into the development and optimization of computational methods, particularly involving machine learning, to streamline the design of better CNS therapeutics. However, analogous efforts developed and validated for CNS radiotracer design are conspicuously limited. In this Perspective, we overview the requirements and challenges of CNS PET tracer design, survey the most promising computational methods for in silico CNS drug design, and bridge these two areas by discussing the potential applications and impact of computational design tools in CNS radiotracer design.

Copper-Mediated Radiocyanation of Unprotected Amino Acids and Peptides

This report describes a copper-mediated radiocyanation of aryl halides that is applicable to complex molecules. This transformation tolerates an exceptionally wide range of functional groups, including unprotected amino acids. As such, it enables the site-specific introduction of [¹¹C]CN into peptides at an iodophenylalanine residue. The use of a diamine-ligated copper(I) mediator is crucial for achieving high radiochemical yield under relatively mild conditions, thus limiting racemization and competing side reactions of other amino acid side chains. The reaction has been scaled and automated to deliver radiolabeled peptides, including analogues of adrenocorticotropic hormone 1-27 (ACTH) and nociceptin (NOP). For instance, this Cu-mediated radiocyanation was leveraged to prepare >40 mCi of [¹¹C]cyano-NOP to evaluate biodistribution in a primate using positron emission tomography. This investigation provides preliminary evidence that nociceptin crosses the blood-brain barrier and shows uptake across all brain regions (SUV > 1 at 60 min post injection), consistent with the known distribution of NOP receptors in the rhesus brain.

SNAr Radiofluorination with In Situ Generated [18F]Tetramethylammonium Fluoride

This report describes a method for the nucleophilic radiofluorination of (hetero)aryl chlorides, (hetero)aryl triflates, and nitroarenes using a combination of [¹⁸F]KF·K_2.2.2 and Me₄NHCO₃ for the in situ formation of a strongly nucleophilic fluorinating reagent (proposed to be [¹⁸F]Me₄NF). This method is applied to 24 substrates bearing diverse functional groups, and it generates [¹⁸F](hetero)aryl fluoride products in good to excellent radiochemical yields in the presence of ambient air/moisture. The reaction is applied to the preparation of ¹⁸F-labeled HQ-415 for potential (pre)clinical use.