Over the last decades, the use of artificial intelligence, machine learning and deep learning in medical fields has skyrocketed. Well known for their results in segmentation, motion management and posttreatment outcome tasks, investigations of machine learning and deep learning models as fast dose calculation or quality assurance tools have been present since 2000. The main motivation for this increasing research and interest in artificial intelligence, machine learning and deep learning is the enhancement of treatment workflows, specifically dosimetry and quality assurance accuracy and time points, which remain important time-consuming aspects of clinical patient management. Since 2014, the evolution of models and architectures for dose calculation has been related to innovations and interest in the theory of information research with pronounced improvements in architecture design. The use of knowledge-based approaches to patient-specific methods has also considerably improved the accuracy of dose predictions. This paper covers the state of all known deep learning architectures and models applied to external radiotherapy with a description of each architecture, followed by a discussion on the performance and future of deep learning predictive models in external radiotherapy.

Brain metastases during pregnancy poses complex conundrum in management. Stereotactic radiosurgery (SRS) offers valuable option to clinicians in this scenario. We reviewed and described the safety and effectiveness of Gamma Knife (GK) SRS in treating a solitary cerebellar metastasis in a patient with recurrent breast cancer at 28 weeks of gestation. Following multidisciplinary discussion, she consented for urgent single session GK SRS to the brain metastasis with 2 cycles of 3-weekly paclitaxel chemotherapy prior to planned delivery at term. Prior to the frame-based treatment, a trial run with dosimeters placed on the superior and inferior parts of foam knee support showed radiation exposure of 3.12 mSv and 1.06 mSv respectively. A prescription dose of 16 Gy at the 50% isodose was delivered using 24 isocentres over 39.7\' of beam on time. The treatment plan had 98% coverage, 89% selectivity and a gradient index of 2.98. Dosimeters placed near the uterine fundus and suprapubic region (consistent with location of fetal head) during the actual treatment recorded 2.83 mSv and 0.27 mSv, which is lower than the trial dosimeter readings. The patient successfully completed SRS treatment and gave birth to a healthy baby two months later. Follow-up MRI at three months interval showed total resolution of the lesion. GK SRS is known for the lowest extracranial dose compared to other SRS modalities. This report and literature review confirmed that GK is a sharp and effective, yet gentle and safe treatment for pregnant patients with brain metastases.

177 Lu radiopharmaceutical therapy is a standardized systemic treatment, with a typical dose of 7.4 GBq per injection, but its response varies from patient to patient. Dosimetry provides the opportunity to personalize treatment, but it requires multiple post-injection images to monitor the radiopharmaceutical\'s biodistribution over time. This imposes an additional imaging burden on centers with limited resources. This review explores methods to lessen this burden by optimizing acquisition types and minimizing the number and duration of imaging sessions. After summarizing the different steps of dosimetry and providing examples of dosimetric workflows for 177 Lu -DOTATATE and 177 Lu -PSMA, we examine dosimetric workflows based on a reduced number of acquisitions, or even just one. We provide a non-exhaustive description of simplified methods and their assumptions, as well as their limitations. Next, we detail the specificities of each normal tissue and tumors, before reviewing dose-response relationships in the literature. In conclusion, we will discuss the current limitations of dosimetric workflows and propose avenues for improvement.

Novel theranostic approaches using radiopharmaceuticals targeting prostate-specific membrane antigen (PSMA) have emerged for treating metastatic castration-resistant prostate cancer. The physical properties and commercial availability of 177Lu make it one of the most used radionuclides for radiopharmaceutical therapy (RPT). In this literature review, we aimed at comparing the dosimetry of the most used [177Lu]Lu-PSMA RPT compounds. Methods: This was a systematic review and metaanalysis of [177Lu]Lu-PSMA RPT (617, I&T, and J591) dosimetry in patients with prostate cancer. Absorbed doses in Gy/GBq for each organ at risk (kidney, parotid and submandibular glands, bone marrow, liver, and lacrimal glands) and for tumor lesions (bone and nonbone lesions) were extracted from included articles. These were used to estimate the pooled average absorbed dose of each agent in Gy/GBq and in Gy/cycle, normalized to the injected activity (per cycle) used in the VISION (7.4 GBq), SPLASH (6.8 GBq), and PROSTACT trials (5.8 GBq). Results: Twenty-nine published articles comprising 535 patients were included in the metaanalysis. The pooled doses (weighted average across studies) of [177Lu]Lu-PSMA-617 and [177Lu]Lu-PSMA-I&T were 4.04 Gy/GBq (17 studies, 297 patients) and 4.70 Gy/GBq (10 studies, 153 patients) for the kidney (P = 0.10), 5.85 Gy/GBq (14 studies, 216 patients) and 2.62 Gy/GBq (5 studies, 86 patients) for the parotids (P < 0.01), 5.15 Gy/GBq (5 studies, 81 patients) and 4.35 Gy/GBq (1 study, 18 patients) for the submandibular glands (P = 0.56), 11.03 Gy/GBq (6 studies, 121 patients) and 19.23 Gy/GBq (3 studies, 53 patients) for the lacrimal glands (P = 0.20), 0.24 Gy/GBq (12 studies, 183 patients) and 0.19 Gy/GBq (4 studies, 68 patients) for the bone marrow (P = 0.31), and 1.11 Gy/GBq (9 studies, 154 patients) and 0.56 Gy/GBq (4 studies, 56 patients) for the liver (P = 0.05), respectively. Average tumor doses tended to be higher for [177Lu]Lu-PSMA-617 than for [177Lu]Lu-PSMA-I&T in soft tissue tumor lesions (4.19 vs. 2.94 Gy/GBq; P = 0.26). Dosimetry data of [177Lu]Lu-J591 were limited to one published study of 35 patients with reported absorbed doses of 1.41, 0.32, and 2.10 Gy/GBq to the kidney, bone marrow, and liver, respectively. Conclusion: In this metaanalysis, there was no significant difference in absorbed dose between [177Lu]Lu-PSMA-I&T and [177Lu]Lu-PSMA-617. There was a possible trend toward a higher kidney dose with [177Lu]Lu-PSMA-I&T and a higher tumor lesion dose with [177Lu]Lu-PSMA-617. It remains unknown whether this finding has any clinical impact. The dosimetry methodologies were strikingly heterogeneous among studies, emphasizing the need for standardization.

Internal dosimetry evaluates the amount and spatial and temporal distributions of radiation energy deposited in tissue from radionuclides within the body. Historically, nuclear medicine had been largely a diagnostic specialty, and the implicitly performed risk-benefit analyses have been straightforward, with relatively low administered activities yielding important diagnostic information whose benefit far outweighs any potential risk associated with the attendant normal-tissue radiation doses. Although dose estimates based on anatomic models and population-average kinetics in this setting may deviate rather significantly from the actual normal-organ doses for individual patients, the large benefit-to-risk ratios are very forgiving of any such inaccuracies. It is in this context that the MIRD schema was originally developed and has been largely applied. The MIRD schema, created and maintained by the MIRD committee of the Society of Nuclear Medicine and Molecular Imaging, comprises the notation, terminology, mathematic formulas, and reference data for calculating tissue radiation doses from radiopharmaceuticals administered to patients. However, with the ongoing development of new radiopharmaceuticals and the increasing therapeutic application of such agents, internal dosimetry in nuclear medicine and the MIRD schema continue to evolve-from population-average and organ-level to patient-specific and suborgan to voxel-level to cell-level dose estimation. This article will review the basic MIRD schema, relevant quantities and units, reference anatomic models, and its adaptation to small-scale and patient-specific dosimetry.

FLASH-radiotherapy delivers a radiation beam a thousand times faster compared to conventional radiotherapy, reducing radiation damage in healthy tissues with an equivalent tumor response. Although not completely understood, this radiobiological phenomenon has been proved in several animal models with a spectrum of all kinds of particles currently used in contemporary radiotherapy, especially electrons. However, all the research teams have performed FLASH preclinical studies using industrial linear accelerator or LINAC commonly employed in conventional radiotherapy and modified for the delivery of ultra-high-dose-rate (UHDRs). Unfortunately, the delivering and measuring of UHDR beams have been proved not to be completely reliable with such devices. Concerns arise regarding the accuracy of beam monitoring and dosimetry systems. Additionally, this LINAC totally lacks an integrated and dedicated Treatment Planning System (TPS) able to evaluate the internal dose distribution in the case of in vivo experiments. Finally, these devices cannot modify dose-time parameters of the beam relevant to the flash effect, such as average dose rate; dose per pulse; and instantaneous dose rate. This aspect also precludes the exploration of the quantitative relationship with biological phenomena. The dependence on these parameters need to be further investigated. A promising advancement is represented by a new generation of electron LINAC that has successfully overcome some of these technological challenges. In this review, we aim to provide a comprehensive summary of the existing literature on in vivo experiments using electron FLASH radiotherapy and explore the promising clinical perspectives associated with this technology.

Theranostics is the combination of two approaches-diagnostics and therapeutics-applied for decades in cancer imaging using radiopharmaceuticals or paired radiopharmaceuticals to image and selectively treat various cancers. The clinical use of theranostics has increased in recent years, with U.S. Food and Drug Administration (FDA) approval of lutetium 177 (177Lu) tetraazacyclododecane tetraacetic acid octreotate (DOTATATE) and 177Lu-prostate-specific membrane antigen vector-based radionuclide therapies. The field of theranostics has imminent potential for emerging clinical applications. This article reviews critical areas of active clinical advancement in theranostics, including forthcoming clinical trials advancing FDA-approved and emerging radiopharmaceuticals, approaches to dosimetry calculations, imaging of different radionuclide therapies, expanded indications for currently used theranostic agents to treat a broader array of cancers, and emerging ideas in the field. Keywords: Molecular Imaging, Molecular Imaging-Cancer, Molecular Imaging-Clinical Translation, Molecular Imaging-Target Development, PET/CT, SPECT/CT, Radionuclide Therapy, Dosimetry, Oncology, Radiobiology © RSNA, 2023.

This paper includes a review of the natural background radiation of the Kingdom of Saudi Arabia. The review deals with natural radioactivity measurements conducted in the past few decades in the Kingdom. The numerous research works reviewed refer to different materials soils processed building material, terrestrial (dwellings) and mining sites. For the measurements, different experimental techniques were adopted. The highest mean specific activity of 238U, 232Th and 40 K in soil samples was found to be 39.0, 25.6, and 343.0 Bq/kg, respectively. While the world average values are 33, 45 and 420 Bq/kg, respectively. For building materials, the highest mean values for 226Ra, 232Th and 40 K were 89, 106 and 773 Bq/kg, respectively. The mean indoor and outdoor dose rates were 455 µGy/y (Riyadh City) and 883 µGy/y (Al-Khamis City), respectively. For the mining sites the mean values for 238U, 226Ra, 228Ra, gross α and gross β, were 0.12, 0.33, 21, 0.78 and 2.44 Bq/kg, respectively. Based on the available data it is concluded that most of the natural background radiation levels in the measured locations were within acceptable limits, while a few isolated locations showed elevated dose rates. This review suggests that new improved radiological survey methods be employed to cover the entire country, and that areas identified with comparably high dose rates be re-assessed, especially, in dwellings and mining sites.

Cerenkov luminescence (CL) is a blue-weighted emission of light produced by a vast array of clinically approved radioisotopes and LINAC accelerators. When β particles (emitted during the decay of radioisotopes) are present in a medium such as water or tissue, they are able to travel faster than the speed of light in that medium and in doing so polarize the molecules around them. Once the particle has left the local area, the polarized molecules relax and return to their baseline state releasing the additional energy as light (luminescence). This blue glow has commonly been used to determine the output of nuclear power plant cores and, in recent years, has found traction in the preclinical and clinical imaging field. This brief review will discuss the technology which has enabled the emergence of the biomedical Cerenkov imaging field, recent pre-clinical studies with potential clinical translation of Cerenkov luminescence imaging (CLI) and the current clinical implementations of the method. Finally, an outlook is given as to the direction in which the field is heading.

Targeted radionuclide therapy (TRT) uses radiopharmaceuticals to specifically irradiate tumor cells while sparing healthy tissue. Response to this treatment highly depends on the absorbed dose. Tumor control probability (TCP) models aim to predict the tumor response based on the absorbed dose by taking into account the different characteristics of TRT. For instance, TRT employs radiation with a high linear energy transfer (LET), which results in an increased effectiveness. Furthermore, a heterogeneous radiopharmaceutical distribution could result in a heterogeneous dose distribution at a tissue, cellular as well as subcellular level, which will generally reduce the tumor response. Finally, the dose rate in TRT is protracted, relatively low, and variable over time. This allows cells to repair more DNA damage, which may reduce the effectiveness of TRT. Within this review, an overview is given on how these characteristics can be included in TCP models, while some experimental findings are also discussed. Many parameters in TCP models are preclinically determined and TCP models also play a role in the preclinical stage of radiopharmaceutical development; however, this all depends critically on the calculated absorbed dose. Accordingly, an overview of the existing preclinical dosimetry methods is given, together with their limitation and applications. It can be concluded that although the theoretical extension of TCP models from external beam radiotherapy towards TRT has been established quite well, the experimental confirmation is lacking. Thus, requiring additional comprehensive studies at the sub-cellular, cellular, and organ level, which should be provided with accurate preclinical dosimetry.