The emergence of Chat Generative Pre-trained Transformer (ChatGPT), a chatbot developed by OpenAI, has garnered interest in the application of generative artificial intelligence (AI) models in the medical field. This review summarizes different generative AI models and their potential applications in the field of medicine and explores the evolving landscape of Generative Adversarial Networks and diffusion models since the introduction of generative AI models. These models have made valuable contributions to the field of radiology. Furthermore, this review also explores the significance of synthetic data in addressing privacy concerns and augmenting data diversity and quality within the medical domain, in addition to emphasizing the role of inversion in the investigation of generative models and outlining an approach to replicate this process. We provide an overview of Large Language Models, such as GPTs and bidirectional encoder representations (BERTs), that focus on prominent representatives and discuss recent initiatives involving language-vision models in radiology, including innovative large language and vision assistant for biomedicine (LLaVa-Med), to illustrate their practical application. This comprehensive review offers insights into the wide-ranging applications of generative AI models in clinical research and emphasizes their transformative potential.

Objective: We aimed to investigate whether 2-[¹⁸F]fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (2-[¹⁸F]FDG PET/CT) can aid in evaluating the risk of malignancy in ampullary tumors detected by endoscopy. Materials and Methods: This single-center retrospective cohort study analyzed 155 patients (79 male, 76 female; mean age, 65.7 ± 12.7 years) receiving 2-[¹⁸F]FDG PET/CT for endoscopy-detected ampullary tumors 5-87 days (median, 7 days) after the diagnostic endoscopy between June 2007 and December 2020. The final diagnosis was made based on histopathological findings. The PET imaging parameters were compared with clinical data and endoscopic features. A model to predict the risk of malignancy, based on PET, endoscopy, and clinical findings, was generated and validated using multivariable logistic regression analysis and an additional bootstrapping method. The final model was compared with standard endoscopy for the diagnosis of ampullary cancer using the DeLong test. Results: The mean tumor size was 17.1 ± 7.7 mm. Sixty-four (41.3%) tumors were benign, and 91 (58.7%) were malignant. Univariable analysis found that ampullary neoplasms with a blood-pool corrected peak standardized uptake value in earlyphase scan (SUVe) ≥ 1.7 were more likely to be malignant (odds ratio [OR], 16.06; 95% confidence interval [CI], 7.13-36.18; P < 0.001). Multivariable analysis identified the presence of jaundice (adjusted OR [aOR], 4.89; 95% CI, 1.80-13.33; P = 0.002), malignant traits in endoscopy (aOR, 6.80; 95% CI, 2.41-19.20; P < 0.001), SUVe ≥ 1.7 in PET (aOR, 5.43; 95% CI, 2.00-14.72; P < 0.001), and PET-detected nodal disease (aOR, 5.03; 95% CI, 1.16-21.86; P = 0.041) as independent predictors of malignancy. The model combining these four factors predicted ampullary cancers better than endoscopic diagnosis alone (area under the curve [AUC] and 95% CI: 0.925 [0.874-0.956] vs. 0.815 [0.732-0.873], P < 0.001). The model demonstrated an AUC of 0.921 (95% CI, 0.816-0.967) in candidates for endoscopic papillectomy. Conclusion: Adding 2-[¹⁸F]FDG PET/CT to endoscopy can improve the diagnosis of ampullary cancer and may help refine therapeutic decision-making, particularly when contemplating endoscopic papillectomy.

Objective: To investigate molecular and functional consequences of additional exposures to iodine- or gadolinium-based contrast agents within 24 hours from the initial intravenous administration of iodine-based contrast agents through an animal study. Materials and Methods: Fifty-six Sprague-Dawley male rats were equally divided into eight groups: negative control, positive control (PC) with single-dose administration of CT contrast agent, and additional administration of either CT or MR contrast agents 2, 4, or 24 hours from initial CT contrast agent injection. A 12 µL/g of iodinated contrast agent or a 0.47 µL/g of gadolinium-based contrast agent were injected into the tail vein. Serum levels of blood urea nitrogen, creatinine, cystatin C (Cys C), and malondialdehyde (MDA) were measured. mRNA and protein levels of kidney injury molecule-1 (KIM-1) and neutrophil gelatinase-associated lipocalin (NGAL) were evaluated. Results: Levels of serum creatinine (SCr) were significantly higher in repeated CT contrast agent injection groups than in PC (0.21 ± 0.02 mg/dL for PC; 0.40 ± 0.02, 0.34 ± 0.03, and 0.41 ± 0.10 mg/dL for 2-, 4-, and 24-hour interval groups, respectively; P < 0.001). There was no significant difference in the average Cys C and MDA levels between PC and repeated CT contrast agent injection groups (Cys C, P = 0.256-0.362; MDA, P > 0.99). Additional doses of MR contrast agent did not make significant changes compared to PC in SCr (P > 0.99), Cys C (P = 0.262), and MDA (P = 0.139-0.771) levels. mRNA and protein levels of KIM-1 and NGAL were not significantly different among additional CT or MR contrast agent groups (P > 0.05). Conclusion: A sufficient time interval, probably more than 24 hours, between repeated contrast-enhanced CT examinations may be necessary to avoid deterioration in renal function. However, conducting contrast-enhanced MRI on the same day as contrast-enhanced CT may not induce clinically significant kidney injury.

Objective: To evaluate the diagnostic performance of susceptibility map-weighted imaging (SMwI) taken in different acquisition planes for discriminating patients with neurodegenerative parkinsonism from those without. Materials and Methods: This retrospective, observational, single-institution study enrolled consecutive patients who visited movement disorder clinics and underwent brain MRI and ¹⁸F-FP-CIT PET between September 2021 and December 2021. SMwI images were acquired in both the oblique (perpendicular to the midbrain) and the anterior commissure-posterior commissure (AC-PC) planes. Hyperintensity in the substantia nigra was determined by two neuroradiologists. ¹⁸F-FP-CIT PET was used as the reference standard. Inter-rater agreement was assessed using Cohen;s kappa coefficient. The diagnostic performance of SMwI in the two planes was analyzed separately for the right and left substantia nigra. Multivariable logistic regression analysis with generalized estimating equations was applied to compare the diagnostic performance of the two planes. Results: In total, 194 patients were included, of whom 105 and 103 had positive results on ¹⁸F-FP-CIT PET in the left and right substantia nigra, respectively. Good inter-rater agreement in the oblique (κ = 0.772/0.658 for left/right) and AC-PC planes (0.730/0.741 for left/right) was confirmed. The pooled sensitivities for two readers were 86.4% (178/206, left) and 83.3% (175/210, right) in the oblique plane and 87.4% (180/206, left) and 87.6% (184/210, right) in the AC-PC plane. The pooled specificities for two readers were 83.5% (152/182, left) and 82.0% (146/178, right) in the oblique plane, and 83.5% (152/182, left) and 86.0% (153/178, right) in the AC-PC plane. There were no significant differences in the diagnostic performance between the two planes (P > 0.05). Conclusion: There are no significant difference in the diagnostic performance of SMwI performed in the oblique and AC-PC plane in discriminating patients with parkinsonism from those without. This finding affirms that each institution may choose the imaging plane for SMwI according to their clinical settings.

Objective: We previously found that the incidence of sarcopenia increased with declining glucose metabolism of muscle in patients with treatment-naïve diffuse large B-cell lymphoma (DLBCL). This study aimed to investigate the relationship between sarcopenia and muscle glucometabolism using ¹⁸F-FDG PET/CT at baseline and end-of-treatment, analyze the changes in these parameters through treatment, and assess their prognostic values. Materials and Methods: The records of 103 patients with DLBCL (median 54 years [range, 21-76]; male:female, 50:53) were retrospectively reviewed. Skeletal muscle area at the third lumbar vertebral (L3) level was measured, and skeletal muscle index (SMI) was calculated to determine sarcopenia, defined as SMI < 44.77 cm²/m² and < 32.50 cm²/m² for male and female, respectively. Glucometabolic parameters of the psoas major muscle, including maximum standardized uptake value (SUVmax) and mean standardized uptake value (SUVmean), were measured at L3 as well. Their changes across treatment were also calculated as ΔSMI, ΔSUVmax, and ΔSUVmean; Δbody mass index was also calculated. Associations between SMI and the metabolic parameters were analyzed, and their associations with progression-free survival (PFS) and overall survival (OS) were identified. Results: The incidence of sarcopenia was 29.1% and 36.9% before and after treatment, respectively. SMI (P = 0.004) was lower, and sarcopenia was more frequent (P = 0.011) at end-of-treatment than at baseline. The SUVmax and SUVmean of muscle were lower (P < 0.001) in sarcopenia than in non-sarcopenia at both baseline and end-of-treatment. ΔSMI was positively correlated with ΔSUVmax of muscle (P = 0.022). Multivariable Cox regression analysis showed that sarcopenia at end-of-treatment was independently negatively associated with PFS (adjusted hazard ratio [95% confidence interval], 2.469 [1.022-5.965]), while sarcopenia at baseline was independently negatively associated with OS (5.051 [1.453-17.562]). Conclusion: Sarcopenic patients had lower muscle glucometabolism, and the muscular and metabolic changes across treatment were positively correlated. Sarcopenia at baseline and end-of-treatment was negatively associated with the prognosis of DLBCL.

Objective: To prospectively evaluate the outcomes of ultrasound (US)-guided radiofrequency ablation (RFA) in tertiary hyperparathyroidism (THPT). Materials and Methods: Patients with THPT underwent RFA between September 2017 and January 2022. Laboratory parameters, including serum intact parathyroid hormone (iPTH) levels, were monitored for 48 months after RFA and compared with the levels at baseline. Complications related to RFA and changes in hyperparathyroidism-related clinical symptoms were recorded before and after RFA. Results: A total of 42 patients with THPT were recruited for this study. Ultimately, 36 patients with renal failure and 2 patients who underwent successful renal transplantation (male:female, 17:21; median age, 54.5 years) were enrolled. The follow-up time was 21.5 ± 19.0 months in the 36 patients with renal failure. In these 36 patients, iPTH levels were significantly decreased to 261.1 pg/mL at 48 months compared with the baseline value of 1284.9 pg/mL (P = 0.012). Persistent hyperparathyroidism, defined as iPTH levels maintained at > 585.0 pg/mL for 6 months after treatment, occurred in 4.0% of patients (1/25). Recurrent hyperparathyroidism, defined as iPTH levels > 585.0 pg/mL after 6 months, were 4.0% (1/25) and 0.0% (0/9) at 6 months and 4 years after treatment, respectively. In two patients with THPT after successful renal transplantation, iPTH decreased from the baseline value of 242.5 and 115.9 pg/mL to 171.0 and 62.0 pg/mL at 6 months after treatment. All complications resolved within 6 months of ablation without medical intervention, except in 10.5% (4/38) patients with permanent hypocalcemia. The overall symptom recovery rate was 58.8% (10/17). The severity scores for bone pain, arthralgia, and itchy skin associated with hyperparathyroidism improved after treatment (P < 0.05). Conclusion: US-guided RFA is an effective and safe alternative to surgery in the treatment of patients with TPTH and improves hyperparathyroidism-related clinical symptoms.

Objective: The current body of evidence lacks clarity regarding the comparative efficacy and safety of radiofrequency ablation (RFA) and microwave ablation (MWA) as minimally invasive treatments for benign thyroid nodules. The primary objective of this study is to clarify these concerns. Materials and Methods: A comprehensive search was conducted using the Cochrane Library, Scopus, Europe PMC, and Medline databases until October 10th, 2023, using a combination of relevant keywords. This study incorporated literature that compared RFA and MWA for benign thyroid nodules. The primary outcome was the volume reduction ratio (VRR) from baseline to follow-up. Secondary outcomes were symptom score, cosmetic score, ablation time, major complications rate, hemorrhage, hoarseness, skin burn, cough, and sympathetic nerve injury. We used Risk of Bias in Non-randomized Studies - of Interventions (ROBINS-I) tool to assess the risk of bias in the included studies. We employed random effects models to analyze the standardized mean difference (SMD) and odds ratio for the presentation of outcomes. Results: Nine studies with 2707 nodules were included. The results of our meta-analysis indicated similar efficacy between RFA and MWA in terms of VRR during the 1 (SMD 0.06; 95% confidence interval [CI]: -0.13 to 0.26; P = 0.52) and 3 (SMD 0.11; 95% CI: -0.03 to 0.25; P = 0.12) months of follow-up. VRR was significantly higher in RFA than in MWA at the 6 (SMD 0.25; 95% CI: 0.06-0.43; P = 0.008) and 12 month of follow-up (SMD 0.38; 95% CI: 0.17 to 0.59; P < 0.001). There were no significant differences between RFA and MWA in symptom scores, cosmetic scores, or the incidence of complications, including hemorrhage, hoarseness, skin burn, cough, and sympathetic nerve injury. Conclusion: RFA showed a higher VRR than MWA at 6 and 12-month follow-ups, with a comparable safety profile.