Vascular endothelial growth factor (VEGF) is associated with the clinical manifestation of Alzheimer's disease (AD). However, the role of the VEGF gene family in neuroprotection is complex due to the number of biological pathways they regulate. This study explored associations between brain expression of VEGF genes with cognitive performance and AD pathology. Genetic, cognitive, and neuropathology data were acquired from the Religious Orders Study and Rush Memory and Aging Project. Expression of ten VEGF ligand and receptor genes was quantified using RNA sequencing of prefrontal cortex tissue. Global cognitive composite scores were calculated from 17 neuropsychological tests. β-amyloid and tau burden were measured at autopsy. Participants (n = 531) included individuals with normal cognition (n = 180), mild cognitive impairment (n = 148), or AD dementia (n = 203). Mean age at death was 89 years and 37% were male. Higher prefrontal cortex expression of VEGFB, FLT4, FLT1, and PGF was associated with worse cognitive trajectories (p ≤ 0.01). Increased expression of VEGFB and FLT4 was also associated with lower cognition scores at the last visit before death (p ≤ 0.01). VEGFB, FLT4, and FLT1 were upregulated among AD dementia compared with normal cognition participants (p ≤ 0.03). All four genes associated with cognition related to elevated β-amyloid (p ≤ 0.01) and/or tau burden (p ≤ 0.03). VEGF ligand and receptor genes, specifically genes relevant to FLT4 and FLT1 receptor signaling, are associated with cognition, longitudinal cognitive decline, and AD neuropathology. Future work should confirm these observations at the protein level to better understand how changes in VEGF transcription and translation relate to neurodegenerative disease.

Purpose In vivo measurement of the spatial distribution of neurofibrillary tangle pathology is critical for early diagnosis and disease monitoring of Alzheimer's disease (AD). Methods Forty-nine participants were scanned with 18 F-PI-2620 PET to examine the distribution of this novel PET ligand throughout the course of AD: 36 older healthy controls (HC) (age range 61 to 86), 11 beta-amyloid+ (Aβ+) participants with cognitive impairment (CI; clinical diagnosis of either mild cognitive impairment or AD dementia, age range 57 to 86), and 2 participants with semantic variant primary progressive aphasia (svPPA, age 66 and 78). Group differences in brain regions relevant in AD (medial temporal lobe, posterior cingulate cortex, and lateral parietal cortex) were examined using standardized uptake value ratios (SUVRs) normalized to the inferior gray matter of the cerebellum. Results SUVRs in target regions were relatively stable 60 to 90 min post-injection, with the exception of very high binders who continued to show increases over time. Robust elevations in 18 F-PI-2620 were observed between HC and Aβ+ CI across all AD regions. Within the HC group, older age was associated with subtle elevations in target regions. Mildly elevated focal uptake was observed in the anterior temporal pole in one svPPA patient. Conclusion Preliminary results suggest strong differences in the medial temporal lobe and cortical regions known to be impacted in AD using 18 F-PI-2620 in patients along the AD trajectory. This work confirms that 18 F-PI-2620 holds promise as a tool to visualize tau aggregations in AD.

No abstract

BACKGROUND AND PURPOSE: Cortical amyloid quantification on PET by using the standardized uptake value ratio is valuable for research studies and clinical trials in Alzheimer disease. However, it is resource intensive, requiring co-registered MR imaging data and specialized segmentation software. We investigated the use of deep learning to automatically quantify standardized uptake value ratio and used this for classification. MATERIALS AND METHODS:Using the Alzheimer's Disease Neuroimaging Initiative dataset, we identified 2582 18 F-florbetapir PET scans, which were separated into positive and negative cases by using a standardized uptake value ratio threshold of 1.1. We trained convolutional neural networks (ResNet-50 and ResNet-152) to predict standardized uptake value ratio and classify amyloid status. We assessed performance based on network depth, number of PET input slices, and use of ImageNet pretraining. We also assessed human performance with 3 readers in a subset of 100 randomly selected cases. RESULTS:We have found that 48% of cases were amyloid positive. The best performance was seen for ResNet-50 by using regression before classification, 3 input PET slices, and pretraining, with a standardized uptake value ratio root-mean-square error of 0.054, corresponding to 95.1% correct amyloid status prediction. Using more than 3 slices did not improve performance, but ImageNet initialization did. The best trained network was more accurate than humans (96% versus a mean of 88%, respectively). CONCLUSIONS:Deep learning algorithms can estimate standardized uptake value ratio and use this to classify 18 F-florbetapir PET scans. Such methods have promise to automate this laborious calculation, enabling quantitative measurements rapidly and in settings without extensive image processing manpower and expertise.

OBJECTIVEImaging evaluation of the cerebral ventricles is important for clinical decision-making in pediatric hydrocephalus. Although quantitative measurements of ventricular size, over time, can facilitate objective comparison, automated tools for calculating ventricular volume are not structured for clinical use. The authors aimed to develop a fully automated deep learning (DL) model for pediatric cerebral ventricle segmentation and volume calculation for widespread clinical implementation across multiple hospitals.METHODSThe study cohort consisted of 200 children with obstructive hydrocephalus from four pediatric hospitals, along with 199 controls. Manual ventricle segmentation and volume calculation values served as “ground truth” data. An encoder-decoder convolutional neural network architecture, in which T2-weighted MR images were used as input, automatically delineated the ventricles and output volumetric measurements. On a held-out test set, segmentation accuracy was assessed using the Dice similarity coefficient (0 to 1) and volume calculation was assessed using linear regression. Model generalizability was evaluated on an external MRI data set from a fifth hospital. The DL model performance was compared against FreeSurfer research segmentation software.RESULTSModel segmentation performed with an overall Dice score of 0.901 (0.946 in hydrocephalus, 0.856 in controls). The model generalized to external MR images from a fifth pediatric hospital with a Dice score of 0.926. The model was more accurate than FreeSurfer, with faster operating times (1.48 seconds per scan).CONCLUSIONSThe authors present a DL model for automatic ventricle segmentation and volume calculation that is more accurate and rapid than currently available methods. With near-immediate volumetric output and reliable performance across institutional scanner types, this model can be adapted to the real-time clinical evaluation of hydrocephalus and improve clinician workflow.