Weidman, David

AbstractBackgroundCross‐modality translation between MRI and PET presents significant challenges due to the distinct mechanisms underlying those modalities. Currently, the leading method for this translation is CycleGAN. Previous studies have proved a strong correlation between BBBMs and brain amyloid status measured by PET. However, the impact of blood‐based biomarkers (BBBMs) on PET image synthesis has not yet been thoroughly evaluated. In this study, we propose Plasma CycleGAN, a generative model based on CycleGAN to synthesize PET images from MRI, while also incorporating BBBMs and other clinical covariates. We show that Plasma CycleGAN outperforms the state‐of‐the‐art CycleGAN for MRI‐to‐PET translation. Our method is the first to integrate BBBMs in a conditional cross modality translation from MRI to PET.MethodOur model was built on CycleGAN architecture, while the backbone was improved by integrating BBBMs as additional conditions in the input domain. To be specific, we introduce a masked perturbation in the MRI image, whose voxel‐level magnitudes are learnable parameters in the neural network. The dataset we used to evaluate our model is downloaded from the ADNI database. The cohort contains 160 subjects with matching BBBM, T1‐weighted MRI images, amyloid PET, and clinical features, including age, sex, weights, etc. The synthesized PET images are compared with the ground truth PET images for performance evaluation using traditional metrics like structural similarity index (SSIM), peak‐signal‐to‐noise ratio (PSNR) and mean square error (MSE). In addition, the Pearson correlation coefficients (PCCs) of the masked SUVR ratios were calculated.ResultWe evaluated the baseline CycleGAN model using MRI input, as well as combined inputs of MRI+BBBM and other clinical features. Our model achieved an SSIM of 0.72±0.16 and PSNR of 22.8±2.3 in PET image synthesis task using MRI+ Aβ42/40, both yielding the best results among all input combinations. MRI+sex achieved the best result using MSE measurement. PCCs of all experimental results ranged from 0.44 to 0.5.ConclusionWe introduce Plasma CycleGAN, the first generative model to integrate BBBMs and clinical features in PET image synthesis from MRI images. In PET image synthesis task, our proposed integrated model outperforms the baseline CycleGAN model.

Abstract Objective There is a dearth of research on neuropsychological functioning and the validity of assessment measures in American Indian (AI) older adults. The present study sought to comprehensively examine neuropsychological functioning in cognitively normal AI older adults in the southwestern USA (i.e., Arizona). Participants and Methods Ninety predominantly female participants (45 AIs and 45 non-Hispanic Whites) aged 44 years and older (mean age of mid-60s) were matched on age, decade, gender, and assessment battery. Participants were enrolled in the Arizona Alzheimer’s Disease Center database. Data obtained included demographics, medical history, psychiatric variables, and raw neuropsychological scores. Analyses included ANCOVAs, chi-square, and stepwise multiple regression. Results AIs generally had lower performance across all neuropsychological measures compared with matched Whites, even after controlling for demographic variables. Performance between groups was most discrepant on several measures of global cognition, attention, executive functioning, and language, while performance was statistically comparable on measures of memory and visuospatial abilities. The AI group had higher proportions of diabetes and obesity, but results showed that higher cardiovascular risk was not predictive of lower cognitive performance with the exception of the Clinical Dementia Rating Scale–Sum of Boxes. Conclusions Findings suggest that older AIs perform lower on many neuropsychological measures compared with non-Hispanic Whites, even after controlling for demographic variables. This suggests that other factors, including language, culture, educational quality, overall health, socioeconomic status, and level of acculturation may be impacting test scores and need to be considered when assessing and diagnosing older AIs.