Review of artificial intelligence clinical applications in Nuclear Medicine.

This paper provides an in-depth analysis of the clinical applications of artificial intelligence (AI) in Nuclear Medicine, focusing on three key areas: neurology, cardiology, and oncology. Beginning with neurology, specifically Alzheimer's disease and Parkinson's disease, the paper examines reviews on diagnosis and treatment planning. The same pattern is followed in cardiology studies. In the final section on oncology, the paper explores the various AI applications in multiple cancer types, including lung, head and neck, lymphoma, and pancreatic cancer.

Artificial intelligence in Nuclear Medicine Physics and Imaging.

No one can deny the significant impact of artificial intelligence (AI) on everyday life, especially in the health sector where it has emerged as a crucial and beneficial tool in Nuclear Medicine (NM) and molecular imaging. The objective of this review is to provide a summary of the various applications of AI in single-photon emission computed tomography (SPECT) and positron emission tomography (PET), with or without anatomical information (CT or magnetic resonance imaging (MRI)). This review analyzes subsets of AI, such as machine learning (ML) and Deep Learning (DL), and elaborates on their applications in NM imaging (NMI) physics, including the generation of attenuation maps, estimation of scattered events, depth of interaction (DOI), time of flight (TOF), NM image reconstruction (optimization of the reconstruction algorithm), and low dose imaging.

A chemical model suggesting the maximum radiolabeled somatostatin analogue tumor uptake, in the presence of unlabeled somatostatin.

Somatostatin analogues (SSA), both radiolabeled and unlabeled play an important role in the management of carcinoid tumors. They are often administered in parallel, the unlabeled analogue for treating the carcinoid tumors' symptoms and the radiolabeled one for imaging tumors foci. There is a debate about when is the optimum time for a somatostatin receptor scintigraphy during treatment. Opinions are divided, with some authors suggesting stopping SSA treatment, while others do not. Our aim was to try to explore pharmacokinetics behind the radiolabeled peptide administration in the presence of circulating in blood unlabeled SSA, by using a model of "law of mass". Applying the pharmacokinetic data from the manufacturers' Prescription Information Sheet in a formula describing competitive binding, led to a reduced uptake for the radiolabeled peptide in the presence of the unlabeled peptide, in comparison with standalone radiolabeled peptide administration, regardless of the total number of available receptors. We provide data that unlabeled somatostatin should be withdrawn for no less than 14 days before the labeled SSA is administered, because biotherapy agents interfere with both diagnostic and therepeutic nuclear medicine procedures. Further research is needed to reach secure conclusions on patient medication management before diagnostic scans or therapeutic administrations in nuclear medicine. In conclusion, by waiting at least 6 half-lives (14 days), after the unlabeled SSA administration, the radiolabeled receptor uptake increased two-fold to three-fold, as compared to simultaneous administration of radiolabeled and unlabeled peptides depending on which SSA was used.

Brown tumors; a possible pitfall in diagnosing metastatic disease.

Brown tumors (BT) are scarcely diagnosed and present a possible diagnostic pitfall in imaging modalities. Imaging modalities and especially positron emission tomography cannot differentiate between brown tumors and metastatic foci and only clinical diagnosis of hyperparathyroidism and histology will support the diagnosis. We describe the histology, clinical expression, significance and the differential diagnosis of BT. We also describe imaging characteristics and imaging techniques for identifying BT. Brown adipose tissue, unrelated to BT may also mimic metastatic disease in imaging modalities.