International pharmacy students' perceptions towards artificial intelligence in medicine-A multinational, multicentre cross-sectional study.

AIMS: To explore international undergraduate pharmacy students' views on integrating artificial intelligence (AI) into pharmacy education and practice. METHODS: This cross-sectional institutional review board-approved multinational, multicentre study comprised an anonymous online survey of 14 multiple-choice items to assess pharmacy students' preferences for AI events in the pharmacy curriculum, the current state of AI education, and students' AI knowledge and attitudes towards using AI in the pharmacy profession, supplemented by 8 demographic queries. Subgroup analyses were performed considering sex, study year, tech-savviness, and prior AI knowledge and AI events in the curriculum using the Mann-Whitney U-test. Variances were reported for responses in Likert scale format. RESULTS: The survey gathered 387 pharmacy student opinions across 16 faculties and 12 countries. Students showed predominantly positive attitudes towards AI in medicine (58%, n = 225) and expressed a strong desire for more AI education (72%, n = 276). However, they reported limited general knowledge of AI (63%, n = 242) and felt inadequately prepared to use AI in their future careers (51%, n = 197). Male students showed more positive attitudes towards increasing efficiency through AI (P = .011), while tech-savvy and advanced-year students expressed heightened concerns about potential legal and ethical issues related to AI (P < .001/P = .025, respectively). Students who had AI courses as part of their studies reported better AI knowledge (P < .001) and felt more prepared to apply it professionally (P < .001). CONCLUSIONS: Our findings underline the generally positive attitude of international pharmacy students towards AI application in medicine and highlight the necessity for a greater emphasis on AI education within pharmacy curricula.

Low-count whole-body PET/MRI restoration: an evaluation of dose reduction spectrum and five state-of-the-art artificial intelligence models.

PURPOSE: To provide a holistic and complete comparison of the five most advanced AI models in the augmentation of low-dose 18F-FDG PET data over the entire dose reduction spectrum. METHODS: In this multicenter study, five AI models were investigated for restoring low-count whole-body PET/MRI, covering convolutional benchmarks - U-Net, enhanced deep super-resolution network (EDSR), generative adversarial network (GAN) - and the most cutting-edge image reconstruction transformer models in computer vision to date - Swin transformer image restoration network (SwinIR) and EDSR-ViT (vision transformer). The models were evaluated against six groups of count levels representing the simulated 75%, 50%, 25%, 12.5%, 6.25%, and 1% (extremely ultra-low-count) of the clinical standard 3 MBq/kg 18F-FDG dose. The comparisons were performed upon two independent cohorts - (1) a primary cohort from Stanford University and (2) a cross-continental external validation cohort from Tübingen University - in order to ensure the findings are generalizable. A total of 476 original count and simulated low-count whole-body PET/MRI scans were incorporated into this analysis. RESULTS: For low-count PET restoration on the primary cohort, the mean structural similarity index (SSIM) scores for dose 6.25% were 0.898 (95% CI, 0.887-0.910) for EDSR, 0.893 (0.881-0.905) for EDSR-ViT, 0.873 (0.859-0.887) for GAN, 0.885 (0.873-0.898) for U-Net, and 0.910 (0.900-0.920) for SwinIR. In continuation, SwinIR and U-Net's performances were also discreetly evaluated at each simulated radiotracer dose levels. Using the primary Stanford cohort, the mean diagnostic image quality (DIQ; 5-point Likert scale) scores of SwinIR restoration were 5 (SD, 0) for dose 75%, 4.50 (0.535) for dose 50%, 3.75 (0.463) for dose 25%, 3.25 (0.463) for dose 12.5%, 4 (0.926) for dose 6.25%, and 2.5 (0.534) for dose 1%. CONCLUSION: Compared to low-count PET images, with near-to or nondiagnostic images at higher dose reduction levels (up to 6.25%), both SwinIR and U-Net significantly improve the diagnostic quality of PET images. A radiotracer dose reduction to 1% of the current clinical standard radiotracer dose is out of scope for current AI techniques.

Molecular MR-Imaging for Noninvasive Quantification of the Anti-Inflammatory Effect of Targeting Interleukin-1ß in a Mouse Model of Aortic Aneurysm.

BACKGROUND: Molecular-MRI is a promising imaging modality for the assessment of abdominal aortic aneurysms (AAAs). Interleukin-1ß (IL-1ß) represents a new therapeutic tool for AAA-treatment, since pro-inflammatory cytokines are key-mediators of inflammation. This study investigates the potential of molecular-MRI to evaluate therapeutic effects of an anti-IL-1ß-therapy on AAA-formation in a mouse-model. METHODS: Osmotic-minipumps were implanted in apolipoprotein-deficient-mice (N = 27). One group (Ang-II+01BSUR group, n = 9) was infused with angiotensin-II (Ang-II) for 4 weeks and received an anti-murine IL-1ß-antibody (01BSUR) 3 times. One group (Ang-II-group, n = 9) was infused with Ang-II for 4 weeks but received no treatment. Control-group (n = 9) was infused with saline and received no treatment. MR-imaging was performed using an elastin-specific gadolinium-based-probe (0.2 mmol/kg). RESULTS: Mice of the Ang-II+01BSUR-group showed a lower aortic-diameter compared to mice of the Ang-II-group and control mice (p < 0.05). Using the elastin-specific-probe, a significant decrease in elastin-destruction was observed in mice of the Ang-II+01BSUR-group. In vivo MR-measurements correlated well with histopathology (y = 0.34x-13.81, R2 = 0.84, p < 0.05), ICP-MS (y = 0.02x+2.39; R2 = 0.81, p < 0.05) and LA-ICP-MS. Immunofluorescence and western-blotting confirmed a reduced IL-1ß-expression. CONCLUSIONS: Molecular-MRI enables the early visualization and quantification of the anti-inflammatory-effects of an IL-1ß-inhibitor in a mouse-model of AAAs. Responders and non-responders could be identified early after the initiation of the therapy using molecular-MRI.

Correlation of Native Liver Parenchyma T1 and T2 Relaxation Times and Liver Synthetic Function Tests: A Pilot Study.

MR relaxometry increasingly contributes to liver imaging. Studies on native relaxation times mainly describe relation to the presence of fibrosis. The hypothesis was that relaxation times are also influenced by other inherent factors, including changes in liver synthesis function. With the approval of the local ethics committee and written informed consent, data from 94 patients referred for liver MR imaging, of which 20 patients had cirrhosis, were included. Additionally to standard sequences, both native T1 and T2 parametric maps and T1 maps in the hepatobiliary phase of gadoxetate disodium were acquired. Associations with laboratory variables were assessed. Altogether, there was a negative correlation between albumin and all acquired relaxation times in cirrhotic patients. In non-cirrhotic patients, only T1 values exhibited a negative correlation with albumin. In all patients, bilirubin correlated significantly with post-contrast T1 relaxation times, whereas native relaxation times correlated only in cirrhotic patients. Evaluating patients with pathological INR values, post-contrast relaxation times were significantly higher, whereas native relaxation times did not correlate. In conclusion, apart from confirming the value of hepatobiliary phase T1 mapping, our results show a correlation of native T1 with serum albumin even in non-cirrhotic liver parenchyma, suggesting a direct influence of liver's synthesis capacity on T1 relaxation times.

Native T1 mapping for assessment of the perilesional zone in metastases and benign lesions of the liver.

Adjacent to hepatic metastases, liver parenchyma is often histopathologically altered even if its visual appearance on native magnetic resonance (MR) images is blunt. Yet, relaxation properties in MR imaging may show structural changes prior to visual alteration, and therefore, the aim of this study was to investigate whether T1 relaxation times in the perilesional zone differ between metastases and benign lesions. A total of 113 patients referred for MRI were included prospectively. Images were assessed for metastases, solid benign lesions and cysts, and regions-of-interest were drawn on T1 maps including the focal lesion and a close (inner perilesional zone = IPZ) and a larger perilesional zone (outer perilesional zone = OPZ). Simple ratios between these zones, as well as a gradient ratio between the IPZ and the entire perilesional zone (EPZ) were calculated. Within the collective, 44 patients had lesions of one or two entities. For metastases, the simple ratio between IPZ and OPZ as well as the mean EPZ gradient was significantly higher than for both solid benign lesions and cysts. Lesion size was not a significant covariate. We conclude, that native T1 properties of the perilesional zones differ significantly between malignant and both solid and cystic benign lesions.

Intracellular accumulation capacity of gadoxetate: initial results for a novel biomarker of liver function.

Previous studies have shown gadoxetate disodium's potential to represent liver function by its retention in the hepatobiliary phase. Additionally, in cardiac imaging, quantitative characterization of altered parenchyma is established by extracellular volume (ECV) calculation with extracellular contrast agents. Therefore, the purpose of our study was to evaluate whether intracellular accumulation capacity (IAC) of gadoxetate disodium derived from ECV calculation provides added scientific value in terms of liver function compared to the established parameter reduction rate (RR). After local review board approval, 105 patients undergoing standard MR examination with gadoxetate disodium were included. Modified Look-Locker sequences were obtained before and 20 min after contrast agent administration. RR and IAC were calculated and correlated with serum albumin, as a marker of synthetic liver function. Correlation was higher between IAC and albumin, than between RR and albumin. Additionally, capacity of both RR and IAC to distinguish between patients with or without liver cirrhosis was investigated, and differed significantly in their respective means between patients with cirrhosis and those without. We concluded, that the formula to calculate ECV can be transferred to calculate IAC of gadoxetate disodium in hepatocytes, and, thereby, IAC may possibly qualify as an imaging-based parameter to estimate synthetic liver function.

MR Angiography of the Head/Neck Vascular System in Mice on a Clinical MRI System.

Background: Magnetic resonance angiography (MRA) represents a clinical reference standard for the in vivo assessment of the vasculature. In this study, the potential of non-contrast-enhanced and contrast-enhanced angiography of the head/neck vasculature in mice on a clinical MR imaging system was tested. Methods: All in vivo magnetic resonance imaging was performed with a 3T clinical system (Siemens). Non-contrast-enhanced (time-of-flight, TOF) and contrast-enhanced angiography (gadofosveset-trisodium, GdT) were performed in C57BL/6J mouse strain. Lumen-to-muscle ratios (LMRs) and area measurements were assessed. Histology was performed as reference standard of all relevant vascular structures. Results: A close correlation between TOF (R 2 = 0.79; p < 0.05) and contrast-enhanced (GdT) angiography (R 2 = 0.92; p < 0.05) with histological area measurements was found. LMRs were comparable between both sequences. Regarding interobserver reproducibility, contrast-enhanced (GdT) angiography yielded a smaller 95% confidence interval and a closer interreader correlation compared to non-contrast-enhanced (TOF) measurements (-0.73-0.89; R 2 = 0.81 vs. -0.55-0.56; R 2 = 0.94). Conclusion: This study demonstrates that non-contrast-enhanced and contrast-enhanced angiographies of the head/neck vasculature of small animals can reliably performed on a clinical 3T MR scanner. Contrast-enhanced angiography enables the visualization of vascular structures with higher intravascular contrast and higher reproducibility.

Improved visualisation of hepatic metastases in gadoxetate disodium-enhanced MRI: Potential of contrast-optimised (phase-sensitive) inversion recovery imaging.

BACKGROUND: Detection of metastases can have a significant impact on therapy. Nevertheless, even in gadoxetate disodium-enhanced MR scans, very small hepatic metastases may be difficult to see. PURPOSE: To investigate the potential of a contrast-optimised (phase-sensitive) inversion recovery MR sequence in gadoxetate disodium-enhanced scans for detection of hepatic metastases. MATERIALS AND METHODS: With institutional review board approval and after written informed consent, 40 patients (18 male, 22 female) with suspected or known hepatic metastases were examined on a 1.5 T MR system. A T1-weighted gradient-echo volumetric-interpolated-breath-hold (VIBE) sequence was acquired as part of the standard imaging protocol 20 minutes after administration of gadoxetate disodium. Additionally, an IR sequence was acquired with an inversion time to suppress native signal from metastases. Overall image quality and delineation of lesions were assessed on VIBE as well as on magnitude-reconstructed (MAG) and phase-sensitive IR (PSIR) sequences. Lesion-to-liver contrast (LLC) was compared between VIBE and MAG images. RESULTS: Overall image quality was high in both VIBE and MAG IR sequences (VIBE 4.275; MAG 4.313), yet significantly lower in PSIR (4.038). Subjective delineation of lesions was higher on MAG and PSIR images compared to VIBE in all size groups with an overall statistically significant difference for VIBE vs. MAG vs. PSIR (p < .001) in the variance analysis. Mean LLC was 0.35±0.01 for VIBE sequences, and 0.73±0.01 for MAG. CONCLUSION: Contrast-optimised PSIR seems to improve imaging characteristics of hepatic metastases in gadoxetate disodium-enhanced scans compared to T1 gradient-echo VIBE sequences.

Feasibility of gadoxetate disodium enhanced 3D T1 MR cholangiography (MRC) with a specific inversion recovery prepulse for the assessment of the hepatobiliary system.

AIM: To compare the potential of a gadoxetate disodium enhanced navigator-triggered 3D T1 magnetic-resonance cholangiography (MRC) sequence with a specific inversion recovery prepulse to T2-weighted MRCP for assessment of the hepatobiliary system. MATERIALS AND METHODS: 30 patients (12 male, 18 female) prospectively underwent conventional navigator-triggered 3D turbo spin-echo T2-weighted MRCP and 3D T1 MRC with a specific inversion pulse to minimise signal from the liver 30 minutes after administration of gadoxetate disodium on a 1.5 T MRI system. For qualitative evaluation, biliary duct depiction was assessed segmentally following a 5-point Likert scale. Visualisation of hilar structures as well as image quality was recorded. Additionally, the extrahepatic bile ducts were assessed quantitatively by calculation of signal-to-noise ratios (SNR). RESULTS: The advantages of T1 3D MRC include reduced affection of image quality by bowel movement and robust depiction of the relative position of the extrahepatic bile ducts in relation to the portal vein and the duodenum compared to T2 MRCP. However, overall T1 3D MRC did not significantly (p > 0.05) improve the biliary duct depiction compared to T2 MRCP in all segments: Common bile duct 4.1 vs. 4.4, right hepatic duct 3.6 vs. 4.2, left hepatic duct 3.5 vs. 4.1. Image quality did not differ significantly (p > 0.05) between both sequences (3.6 vs. 3.5). SNR measurements for the hepatobiliary system did not differ significantly (p > 0.05) between navigator-triggered T1 3D MRC and T2 MRCP. CONCLUSIONS: This preliminary study demonstrates that T1 3D MRC of a specific inversion recovery prepulse has potential to complement T2 MRCP, especially for the evaluation of liver structures close to the hilum in the diagnostic work-up of the biliary system in patients receiving gadoxetate disodium.