Granzyme B PET Imaging for Assessment of Disease Activity in Inflammatory Bowel Disease.

Developing a noninvasive imaging method to detect immune system activation with a high temporal resolution is key to improving inflammatory bowel disease (IBD) management. In this study, granzyme B (GZMB), typically released from cytotoxic T and natural killer cells, was targeted using PET with 68Ga-NOTA-GZP (where GZP is ß-Ala-Gly-Gly-Ile-Glu-Phe-Asp-CHO) to detect early intestinal inflammation in murine models of colitis. Methods: Bioinformatic analysis was used to assess the potential of GZMB as a biomarker for detecting IBD and predicting response to treatment. Human active and quiescent Crohn disease and ulcerative colitis tissues were stained for GZMB. We used IL-10-/- mice treated with dextran sulfate sodium (DSS) as an IBD model, wild-type C57BL/6J mice as a control, and anti-tumor necrosis factor as therapy. We used a murine GZMB-binding peptide conjugated to a NOTA chelator (NOTA-GZP) labeled with 68Ga as the PET tracer. PET imaging was conducted at 1, 3, and 4 wk after colitis induction to evaluate temporal changes. Results: Bioinformatic analysis showed that GZMB gene expression is significantly upregulated in human ulcerative colitis and Crohn disease compared with the noninflamed bowel by 2.98-fold and 1.92-fold, respectively; its expression is lower by 2.16-fold in treatment responders than in nonresponders. Immunofluorescence staining of human tissues demonstrated a significantly higher GZMB in patients with active than with quiescent IBD (P = 0.032).68Ga-NOTA-GZP PET imaging showed significantly increased bowel uptake in IL-10-/- mice with DSS-induced colitis compared with vehicle-treated IL-10-/- mice (SUVmean, 0.75 vs. 0.24; P < 0.001) and both vehicle- and DSS-treated wild-type mice (SUVmean, 0.26 and 0.37; P < 0.001). In the IL-10-/- DSS-induced colitis model, the bowel PET probe uptake decreased in response to treatment with tumor necrosis factor-α (SUVmean, 0.32; P < 0.001). There was a 4-fold increase in colonic uptake of 68Ga-NOTA-GZP in the colitis model compared with the control 1 wk after colitis induction. The uptake gradually decreased to approximately 2-fold by 4 wk after IBD induction; however, the inflamed bowel uptake remained significantly higher than control at all time points (week 4 SUVmean, 0.23 vs. 0.08; P = 0.001). Conclusion: GZMB is a promising biomarker to detect active IBD and predict response to treatment. This study provides compelling evidence to translate GZMB PET for imaging IBD activity in clinical settings.

Mechanism of Action and Translational Potential of (S)-Meclizine in Preemptive Prophylaxis Against Stroke.

BACKGROUND: Mild chemical inhibition of mitochondrial respiration can confer resilience against a subsequent stroke or myocardial infarction, also known as preconditioning. However, the lack of chemicals that can safely inhibit mitochondrial respiration has impeded the clinical translation of the preconditioning concept. We previously showed that meclizine, an over-the-counter antivertigo drug, can toggle metabolism from mitochondrial respiration toward glycolysis and protect against ischemia-reperfusion injury in the brain, heart, and kidney. Here, we examine the mechanism of action of meclizine and report the efficacy and improved safety of the (S) enantiomer. METHODS: We determined the anoxic depolarization latency, tissue and neurological outcomes, and glucose uptake using micro-positron emission tomography after transient middle cerebral artery occlusion in mice pretreated (-17 and -3 hours) with either vehicle or meclizine. To exclude a direct effect on tissue excitability, we also examined spreading depression susceptibility. Furthermore, we accomplished the chiral synthesis of (R)- and (S)-meclizine and compared their effects on oxygen consumption and histamine H1 receptor binding along with their brain concentrations. RESULTS: Micro-positron emission tomography showed meclizine increases glucose uptake in the ischemic penumbra, providing the first in vivo evidence that the neuroprotective effect of meclizine indeed stems from its ability to toggle metabolism toward glycolysis. Consistent with reduced reliance on oxidative phosphorylation to sustain the metabolism, meclizine delayed anoxic depolarization onset after middle cerebral artery occlusion. Moreover, the (S) enantiomer showed reduced H1 receptor binding, a dose-limiting side effect for the racemate, but retained its effect on mitochondrial respiration. (S)-meclizine was at least as efficacious as the racemate in delaying anoxic depolarization onset and decreasing infarct volumes after middle cerebral artery occlusion. CONCLUSIONS: Our data identify (S)-meclizine as a promising new drug candidate with high translational potential as a chemical preconditioning agent for preemptive prophylaxis in patients with high imminent stroke or myocardial infarction risk.

Artificial Intelligence for PET and SPECT Image Enhancement.

Nuclear medicine imaging modalities such as PET and SPECT are confounded by high noise levels and low spatial resolution, necessitating postreconstruction image enhancement to improve their quality and quantitative accuracy. Artificial intelligence (AI) models such as convolutional neural networks, U-Nets, and generative adversarial networks have shown promising outcomes in enhancing PET and SPECT images. This review article presents a comprehensive survey of state-of-the-art AI methods for PET and SPECT image enhancement and seeks to identify emerging trends in this field. We focus on recent breakthroughs in AI-based PET and SPECT image denoising and deblurring. Supervised deep-learning models have shown great potential in reducing radiotracer dose and scan times without sacrificing image quality and diagnostic accuracy. However, the clinical utility of these methods is often limited by their need for paired clean and corrupt datasets for training. This has motivated research into unsupervised alternatives that can overcome this limitation by relying on only corrupt inputs or unpaired datasets to train models. This review highlights recently published supervised and unsupervised efforts toward AI-based PET and SPECT image enhancement. We discuss cross-scanner and cross-protocol training efforts, which can greatly enhance the clinical translatability of AI-based image enhancement tools. We also aim to address the looming question of whether the improvements in image quality generated by AI models lead to actual clinical benefit. To this end, we discuss works that have focused on task-specific objective clinical evaluation of AI models for image enhancement or incorporated clinical metrics into their loss functions to guide the image generation process. Finally, we discuss emerging research directions, which include the exploration of novel training paradigms, curation of larger task-specific datasets, and objective clinical evaluation that will enable the realization of the full translation potential of these models in the future.

Advantages of a Photodiode Detector Endoscopy System in Fluorescence-Guided Percutaneous Liver Biopsies.

Image-guided liver biopsies can improve their success rate when combined with the optical detection of Indocyanine Green (ICG) fluorescence accumulated in tumors. Previous works used a camera coupled to a thin borescope to capture and quantify images from fluorescence emission during procedures; however, light-scattering prevented the formation of sharp images, and the time response for weakly fluorescent tumors was very low. Instead, replacing the camera with a photodiode detector shows an improved temporal resolution in a more compact and lighter device. This work presents the new design in a comparative study between both detection technologies, including an assessment of the temporal response and sensitivity to the presence of background fluorescence.

DNA Damage by Radiopharmaceuticals and Mechanisms of Cellular Repair.

DNA is an organic molecule that is highly vulnerable to chemical alterations and breaks caused by both internal and external factors. Cells possess complex and advanced mechanisms, including DNA repair, damage tolerance, cell cycle checkpoints, and cell death pathways, which together minimize the potentially harmful effects of DNA damage. However, in cancer cells, the normal DNA damage tolerance and response processes are disrupted or deregulated. This results in increased mutagenesis and genomic instability within the cancer cells, a known driver of cancer progression and therapeutic resistance. On the other hand, the inherent instability of the genome in rapidly dividing cancer cells can be exploited as a tool to kill by imposing DNA damage with radiopharmaceuticals. As the field of targeted radiopharmaceutical therapy (RPT) is rapidly growing in oncology, it is crucial to have a deep understanding of the impact of systemic radiation delivery by radiopharmaceuticals on the DNA of tumors and healthy tissues. The distribution and activation of DNA damage and repair pathways caused by RPT can be different based on the characteristics of the radioisotope and molecular target. Here we provide a comprehensive discussion of the biological effects of RPTs, with the main focus on the role of varying radioisotopes in inducing direct and indirect DNA damage and activating DNA repair pathways.

Spach Transformer: Spatial and Channel-wise Transformer Based on Local and Global Self-attentions for PET Image Denoising.

Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely used to improve PET image quality. Though successful and efficient in local feature extraction, CNN cannot capture long-range dependencies well due to its limited receptive field. Global multi-head self-attention (MSA) is a popular approach to capture long-range information. However, the calculation of global MSA for 3D images has high computational costs. In this work, we proposed an efficient spatial and channel-wise encoder-decoder transformer, Spach Transformer, that can leverage spatial and channel information based on local and global MSAs. Experiments based on datasets of different PET tracers, i.e., 18F-FDG, 18F-ACBC, 18F-DCFPyL, and 68Ga-DOTATATE, were conducted to evaluate the proposed framework. Quantitative results show that the proposed Spach Transformer framework outperforms state-of-the-art deep learning architectures.

Theranostics in targeting fibroblast activation protein bearing cells: Progress and challenges.

Cancer cells are surrounded by a complex and highly dynamic tumor microenvironment (TME). Cancer-associated fibroblasts (CAFs), a critical component of TME, contribute to cancer cell proliferation as well as metastatic spread. CAFs express a variety of biomarkers, which can be targeted for detection and therapy. Most importantly, CAFs express high levels of fibroblast activation protein (FAP) which contributes to progression of cancer, invasion, metastasis, migration, immunosuppression, and drug resistance. As a consequence, FAP is an attractive theranostic target. In this review, we discuss the latest advancement in targeting FAP in oncology using theranostic biomarkers and imaging modalities such as single-photon emission computed tomography (SPECT), positron emission tomography (PET), computed tomography (CT), fluorescence imaging, and magnetic resonance imaging (MRI).

Deep learning based automated delineation of the intraprostatic gross tumour volume in PSMA-PET for patients with primary prostate cancer.

PURPOSE: With the increased use of focal radiation dose escalation for primary prostate cancer (PCa), accurate delineation of gross tumor volume (GTV) in prostate-specific membrane antigen PET (PSMA-PET) becomes crucial. Manual approaches are time-consuming and observer dependent. The purpose of this study was to create a deep learning model for the accurate delineation of the intraprostatic GTV in PSMA-PET. METHODS: A 3D U-Net was trained on 128 different 18F-PSMA-1007 PET images from three different institutions. Testing was done on 52 patients including one independent internal cohort (Freiburg: n = 19) and three independent external cohorts (Dresden: n = 14 18F-PSMA-1007, Boston: Massachusetts General Hospital (MGH): n = 9 18F-DCFPyL-PSMA and Dana-Farber Cancer Institute (DFCI): n = 10 68Ga-PSMA-11). Expert contours were generated in consensus using a validated technique. CNN predictions were compared to expert contours using Dice similarity coefficient (DSC). Co-registered whole-mount histology was used for the internal testing cohort to assess sensitivity/specificity. RESULTS: Median DSCs were Freiburg: 0.82 (IQR: 0.73-0.88), Dresden: 0.71 (IQR: 0.53-0.75), MGH: 0.80 (IQR: 0.64-0.83) and DFCI: 0.80 (IQR: 0.67-0.84), respectively. Median sensitivity for CNN and expert contours were 0.88 (IQR: 0.68-0.97) and 0.85 (IQR: 0.75-0.88) (p = 0.40), respectively. GTV volumes did not differ significantly (p > 0.1 for all comparisons). Median specificity of 0.83 (IQR: 0.57-0.97) and 0.88 (IQR: 0.69-0.98) were observed for CNN and expert contours (p = 0.014), respectively. CNN prediction took 3.81 seconds on average per patient. CONCLUSION: The CNN was trained and tested on internal and external datasets as well as histopathology reference, achieving a fast GTV segmentation for three PSMA-PET tracers with high diagnostic accuracy comparable to manual experts.

Addition of Peptide Receptor Radiotherapy to Immune Checkpoint Inhibition Therapy Improves Outcomes in Neuroendocrine Tumors.

Neuroendocrine tumors (NETs) are often diagnosed in advanced stages. Despite the advances in treatment approaches, including somatostatin analogs and peptide receptor radionuclide therapy (PRRT), these patients have no curative treatment option. Moreover, immunotherapy often yields modest results in NETs. We investigated whether combining PRRT using [177Lu]DOTATATE and immune checkpoint inhibition therapy improves treatment response in NETs. Methods: A gastroenteropancreatic NET model was generated by subcutaneous implantation of human QGP-1 cells in immune-reconstituted NOD.Cg-Prkdcscid Il2rgtm1Wjl /SzJ mice engrafted with human peripheral blood mononuclear cells (n = 96). Mice were randomly assigned to receive pembrolizumab (anti-PD1), [177Lu]DOTATATE (PRRT), simultaneous anti-PD1 and PRRT (S-PRRT), anti-PD1 on day 0 followed by PRRT on day 3 (delayed PRRT [D-PRRT]), PRRT on day 0 followed by anti-PD1 (early PRRT [E-PRRT]), or vehicle as control (n = 12/group). Human granzyme-B-specific [68Ga]NOTA-hGZP PET/MRI was performed before and 6 d after treatment initiation, as an indicator of T-cell activation. Response to treatment was based on tumor growth over 21 d and on histologic analyses of extracted tissues on flow cytometry for T cells, hematoxylin and eosin staining, and immunohistochemical staining. Results: [68Ga]NOTA-hGZP PET/MRI showed significantly increased uptake in tumors treated with E-PRRT, S-PRRT, and anti-PD1 on day 6 compared with baseline (SUVmax: 3.36 ± 0.42 vs. 0.73 ± 0.23; 2.36 ± 0.45 vs. 0.76 ± 0.30; 2.20 ± 0.20 vs. 0.72 ± 0.28, respectively; P < 0.001), whereas no significant change was seen in PET parameters in the D-PRRT, PRRT, or vehicle groups (P > 0.05). Ex vivo analyses confirmed the PET results showing the highest granzyme-B levels and T cells (specifically CD8-positive effector T cells) in the E-PRRT group, followed by the S-PRRT and anti-PD1 groups. Tumor growth follow-up showed the most significant tumor size reduction in the E-PRRT group (baseline to day 21, 205.00 ± 30.70 mm3 vs. 78.00 ± 11.75 mm3; P = 0.0074). Tumors showed less growth reduction in the PRRT, D-PRRT, and S-PRRT groups than in the E-PRRT group (P < 0.0001). The vehicle- and anti-PD-1-treated tumors showed continued growth. Conclusion: Combination of PRRT and anti-PD1 shows the most robust inflammatory response to NETs and a better overall outcome than immune checkpoint inhibition or PRRT alone. The most effective regimen is PRRT preceding anti-PD1 administration by several days.

COVID-19: Findings in nuclear medicine from head to toe.

COVID-19 is a multisystemic disease, and hence its potential manifestations on nuclear medicine imaging can extend beyond the lung. Therefore, it is important for the nuclear medicine physician to recognize these manifestations in the clinic. While FDG-PET/CT is not indicated routinely in COVID-19 evaluation, its unique capability to provide a functional and anatomical assessment of the entire body means that it can be a powerful tool to monitor acute, subacute, and long-term effects of COVID-19. Single-photon scintigraphy is routinely used to assess conditions such as pulmonary embolism, cardiac ischemia, and thyroiditis, and COVID-19 may present in these studies. The most common nuclear imaging finding of COVID-19 vaccination to date is hypermetabolic axillary lymphadenopathy. This may pose important diagnostic and management dilemmas in oncologic patients, particularly those with malignancies where the axilla constitutes a lymphatic drainage area. This article aims to summarize the relevant literature published since the beginning of the pandemic on the intersection between COVID-19 and nuclear medicine.

Targeted Molecular Imaging as a Biomarker in Urologic Oncology.

Urologic malignancies constitute a large portion of annually diagnosed cancers. Timely diagnosis, accurate staging, and assessment of tumor heterogeneity are essential to devising the best treatment strategy for individual patients. The high sensitivity of molecular imaging allows for early and sensitive detection of lesions that were not readily detectable using conventional imaging techniques. Moreover, molecular imaging enables the interrogation of molecular processes used in targeted cancer therapies and predicts cancer response to treatment. Here we review the current advancements in molecular imaging of urologic cancers, including prostatic, vesical, renal testicular, and ureteral cancers.

Integrating Theranostics Into Patient Care Pathways: AJR Expert Panel Narrative Review.

Theranostics describes the coupling of a diagnostic biomarker and a therapeutic agent (i.e., a theranostic pair) that have a common target in tumor cells or their microenvironment. The term is increasingly associated with in vivo nuclear medicine oncologic applications that couple diagnostic imaging by means of gamma radiation with concomitant localized high-energy particulate radiation to a tissue expressing the common target. Several theranostic pairs have been translated into clinical practice in the United States and are poised to become a mainstay of cancer treatment. The purposes of this article are to review experience with theranostics for solid-organ malignancies and to address the practical integration into care pathways of ß-emitting therapies that include somatostatin analogue radioligands for neuroendocrine tumors, PSMA-directed therapy for prostate cancer, and 131I-MIBG therapy for tumors of neural crest origin. Toxicities related to theranostics administration and indications for cessation of therapy in patients who experience adverse events are also discussed. A multidisciplinary team-based approach for identifying patients most likely to respond to these agents, determining the optimal time for therapy delivery, and managing patient care throughout the therapeutic course is critical to the success of a radiotheranostic program.

HER3 PET Imaging Predicts Response to Pan Receptor Tyrosine Kinase Inhibition Therapy in Gastric Cancer.

PURPOSE: New generation of receptor tyrosine kinase inhibitors (RTKIs) have shown to improve survival in many solid tumors. However, an imaging biomarker is needed for patient selection and prediction of treatment response. This study evaluates the use of quantitative changes of HER3 on 68 Ga-NOTA-HER3P1 PET/MRI for prediction of early response to pan-RTKIs in gastric cancer (GCa). PROCEDURES: GCa cell lines were evaluated for expression of RTKs, and downstream signaling pathways (AKT and MAPK). Cell viability was assessed following 24-72 h of treatment with 0.01-1 µmol/L of afatinib, a pan-RTKI. HER3-expressing afatinib-sensitive (NCI-N87) and resistant cells (SNU16) were selected for evaluation of changes in RTKs expression and downstream pathways, with 24-72 h of 0.1 µmol/L afatinib treatment. 68 Ga-NOTA-HER3P1 PET/MRI was performed in subcutaneous NCI-N87 and SNU16 xenografts (nu:nu, n = 12/group) at baseline and 4 days after afatinib treatment (10 mg/kg, PO, daily). Temporal changes in PET measures were correlated to HER3 expression in tumors, tumor growth rate, and treatment response. RESULTS: With afatinib therapy, NCI-N87 cells showed increased total HER3 expression, and reduction of other RTKs and downstream nodes within 72 h, while SNU16 cells showed no significant change in total HER3 and downstream nodes. 68 Ga-HER3P1 PET/MRI showed increased uptake in NCI-N87 and no significant change in SNU16 tumors (day 4 vs. baseline SUVmean: 3.8 ± 0.7 vs. 1.6 ± 0.6, p < 0.05 in NCI-N87, and 1.5 ± 0.7 vs. 1.7 ± 0.7, p > 0.05 in SNU16). These findings were in concordance with HER3 expression in histopathological analyses and tumor growth over 3 weeks of treatment (mean tumor volume in treated vs. control: 11 ± 17 mm3 vs. 293 ± 79 mm3, p < 0.001 in NCI-N87, and 238 ± 91 mm3 vs. 282 ± 35 mm3, p > 0.05 in SNU16). CONCLUSIONS: Quantitative changes in HER3 PET could be used to predict response to pan-RTKI within few days after initiation of treatment and can help with personalizing GCa management.

Immune Checkpoint Inhibitor-Mediated Cancer Theranostics with Radiolabeled Anti-Granzyme B Peptide.

Although immune checkpoint inhibitors (ICI) have revolutionized cancer management, patient response can be heterogeneous, and the development of ICI resistance is increasingly reported. Novel treatment strategies are necessary not only to expand the use of ICI to previously unresponsive tumor types but also to overcome resistance. Targeted radionuclide therapy may synergize well with ICIs since it can promote a pro-inflammatory tumor microenvironment. We investigated the use of a granzyme B targeted peptide (GZP) as a cancer theranostic agent, radiolabeled with 68Ga (68Ga-GZP) as a PET imaging agent and radiolabeled with 90Y (90Y-GZP) as a targeted radionuclide therapy agent for combinational therapy with ICI in murine models of colon cancer. Our results demonstrate that GZP increasingly accumulates in tumor tissue after ICI and that the combination of ICI with 90Y-GZP promotes a dose-dependent response, achieving curative response in some settings and increased overall survival.

Hyperpolarized [1-13C]Pyruvate Magnetic Resonance Spectroscopic Imaging for Evaluation of Early Response to Tyrosine Kinase Inhibition Therapy in Gastric Cancer.

PURPOSE: To evaluate the use of hyperpolarized [1-13C]pyruvate magnetic resonance spectroscopic imaging (HP-13C MRSI) for quantitative measurement of early changes in glycolytic metabolism and its ability to predict response to pan-tyrosine kinase inhibitor (Pan-TKI) therapy in gastric cancer (GCa). PROCEDURES: Pan-TKI afatinib-sensitive NCI-N87 and resistant SNU16 human GCa cells were assessed for GLUT1, hexokinase-II (HKII), lactate dehydrogenase (LDHA), phosphorylated AKT (pAKT), and phosphorylated MAPK (pMAPK) at 0-72 h of treatment with 0.1 µM afatinib. Subcutaneous NCI-N87 tumor-bearing nude mice underwent [18F]FDG PET/MRI and HP-13C MRSI at baseline and 4 days after treatment with afatinib 10 mg/kg/day or vehicle (n = 10/group). Changes in PET and HP-13C MRSI metabolic parameters were compared between the two groups. Imaging findings were correlated with tumor growth and histopathology over 3 weeks of treatment. RESULTS: In vitro analysis showed a continuous decrease in LDHA, pAKT, and pMAPK in NCI-N87 compared to SNU16 cells within 72 h of treatment with afatinib, without a significant change in GLUT1 and HKII in either cell type. [18F]FDG PET of NCI-N87 tumors showed no significant change in PET measures at baseline and day 4 of treatment in either treatment group (SUVmean day 4/day 0: 2.7 ± 0.42/2.34 ± 0.38, p = 0.57 in the treated group vs. 1.73 ± 0.66/2.24 ± 0.43, p = 0.4 in the control group). HP-13C MRSI demonstrated significantly decreased lactate-to-pyruvate ratio (L/P) in treated tumors (L/P day 4/day 0: 0.83 ± 0.30/1.10 ± 0.20, p = 0.012 vs. 0.94 ± 0.20/0.98 ± 0.30, p = 0.75, in the treated vs. control group, respectively). Response to afatinib was confirmed with decreased tumor size over 3 weeks (11.10 ± 16.50 vs. 293.00 ± 79.30 mm3, p < 0.001, treated group vs. control group, respectively) and histopathologic evaluation. CONCLUSIONS: HP-13C MRSI is a more representative biomarker of early metabolic changes in response to pan-TKI in GCa than [18F]FDG PET and could be used for early prediction of response to targeted therapies.

Influence of Thin Film Deposition on AFM Cantilever Tips in Adhesion and Young's Modulus of MEMS Surfaces.

Adhesion is a critical factor in microelectromechanical systems (MEMSs) and is influenced by many parameters. In important fields, such as microassembly, an improved understanding of adhesion can result in higher precision. This study examines the influence of deposition of gold and titanium onto the atomic force microscope (AFM) tips in adhesion forces and Young's modulus, between a few MEMS substrates (silicon, gold, and silver) and the AFM tips. It was found that, except for gold substrate, an AFM tip coated with gold has the highest adhesion force of 42.67 nN for silicon substrates, whereas the titanium-coated AFM tip decreases the force for all the samples. This study suggests that such changes must be taken into account while studying the adhesion force. The final results indicate that utilizing gold substrate with titanium AFM tip led to the lowest adhesion force, which could be useful in adhesion force measurement during microassembly.

Incorporating PSMA-Targeting Theranostics Into Personalized Prostate Cancer Treatment: a Multidisciplinary Perspective.

Recent developments in prostate-specific membrane antigen (PSMA) targeted diagnostic imaging and therapeutics (theranostics) promise to advance the management of primary, biochemically recurrent, and metastatic prostate cancer. In order to maximize the clinical impact of PSMA-targeted theranostics, a coordinated approach between the clinical stakeholders involved in prostate cancer management is required. Here, we present a vision for multidisciplinary use of PSMA theranostics from the viewpoints of nuclear radiology, medical oncology, urology, and radiation oncology. We review the currently available and forthcoming PSMA-based imaging and therapeutics and examine current and potential impacts on prostate cancer management from early localized disease to advanced treatment-refractory disease. Finally, we highlight the clinical and research opportunities related to PSMA-targeted theranostics and describe the importance of multidisciplinary collaboration in this space.

Artificial Intelligence and the Future of Diagnostic and Therapeutic Radiopharmaceutical Development:: In Silico Smart Molecular Design.

Novel diagnostic and therapeutic radiopharmaceuticals are increasingly becoming a central part of personalized medicine. Continued innovation in the development of new radiopharmaceuticals is key to sustained growth and advancement of precision medicine. Artificial intelligence has been used in multiple fields of medicine to develop and validate better tools for patient diagnosis and therapy, including in radiopharmaceutical design. In this review, we first discuss common in silico approaches and focus on their usefulness and challenges in radiopharmaceutical development. Next, we discuss the practical applications of in silico modeling in design of radiopharmaceuticals in various diseases.