Alzheimer's disease (AD) is a progressive neurodegenerative disorder that is mostly prevalent in people older than 65 years. The hippocampus is a widely studied region of interest (ROI) for a number of reasons, such as memory function analysis, stress development observation and neurological disorder investigation. Moreover, hippocampal volume atrophy is known to be linked with Alzheimer's disease. On the other hand, several biomarkers, such as amyloid beta (aß ₄₂ ) protein, tau, phosphorylated tau and hippocampal volume atrophy, are being used to diagnose AD. In this research work, we have proposed a method to diagnose AD based on slice-wise volumetric features extracted from the left and right hippocampi of structural magnetic resonance imaging (sMRI) data. The proposed method is an aggregation of a convolutional neural network (CNN) model with a deep neural network (DNN) model. The left and right hippocampi have been localized automatically using a two-stage ensemble Hough-CNN. The localized hippocampal positions are used to extract (80 × 80x80 voxels) 3-D patches. The 2-D slices are then separated from the 3-D patches along axial, sagittal, and coronal views. The pre-processed 2-D patches are used to extract volumetric features from each slice by using a discrete volume estimation convolutional neural network (DVE-CNN) model. The extracted volumetric features have been used to train and test the classification network. The proposed approach has achieved average weighted classification accuracies of 94.82% and 94.02% based on the extracted volumetric features attributed to the left and right hippocampi, respectively. In addition, it has achieved area under the curve (AUC) values of 92.54% and 90.62% for the left and right hippocampi, respectively. Our method has outperformed the other methods by a certain margin in the same dataset.

Variants in the APOE gene region may explain ethnic differences in the association of Alzheimer’s disease (AD) with ε4. Ethnic differences in allele frequencies for three APOE region SNPs (single nucleotide polymorphisms) were identified and tested for association in 19,398 East Asians (EastA), including Koreans and Japanese, 15,836 European ancestry (EuroA) individuals, and 4985 African Americans, and with brain imaging measures of cortical atrophy in sub-samples of Koreans and EuroAs. Among ε4/ε4 individuals, AD risk increased substantially in a dose-dependent manner with the number of APOE promoter SNP rs405509 T alleles in EastAs (TT: OR (odds ratio) = 27.02, p = 8.80 × 10⁻⁹⁴; GT: OR = 15.87, p = 2.62 × 10⁻⁹) and EuroAs (TT: OR = 18.13, p = 2.69 × 10⁻¹⁰⁸; GT: OR = 12.63, p = 3.44 × 10⁻⁶⁴), and rs405509-T homozygotes had a younger onset and more severe cortical atrophy than those with G-allele. Functional experiments using APOE promoter fragments demonstrated that TT lowered APOE expression in human brain and serum. The modifying effect of rs405509 genotype explained much of the ethnic variability in the AD/ε4 association, and increasing APOE expression might lower AD risk among ε4 homozygotes.

Background: Neuropsychological tests (NPTs) are important tools for informing diagnoses of cognitive impairment (CI). However, interpreting NPTs requires specialists and is thus time-consuming. To streamline the application of NPTs in clinical settings, we developed and evaluated the accuracy of a machine learning algorithm using multi-center NPT data. Methods: Multi-center data were obtained from 14,926 formal neuropsychological assessments (Seoul Neuropsychological Screening Battery), which were classified into normal cognition (NC), mild cognitive impairment (MCI) and Alzheimer’s disease dementia (ADD). We trained a machine learning model with artificial neural network algorithm using TensorFlow (https://www.tensorflow.org) to distinguish cognitive state with the 46-variable data and measured prediction accuracies from 10 randomly selected datasets. The features of the NPT were listed in order of their contribution to the outcome using Recursive Feature Elimination. Results: The ten times mean accuracies of identifying CI (MCI and ADD) achieved by 96.66 ± 0.52% of the balanced dataset and 97.23 ± 0.32% of the clinic-based dataset, and the accuracies for predicting cognitive states (NC, MCI or ADD) were 95.49 ± 0.53 and 96.34 ± 1.03%. The sensitivity to the detection CI and MCI in the balanced dataset were 96.0 and 96.0%, and the specificity were 96.8 and 97.4%, respectively. The ‘time orientation’ and ‘3-word recall’ score of MMSE were highly ranked features in predicting CI and cognitive state. The twelve features reduced from 46 variable of NPTs with age and education had contributed to more than 90% accuracy in predicting cognitive impairment. Conclusions: The machine learning algorithm for NPTs has suggested potential use as a reference in differentiating cognitive impairment in the clinical setting.

Alzheimer's disease (AD), characterized by the abnormal accumulation of amyloid beta (Aβ), is gradually increasing globally. Given that AD is considered a neuroinflammatory disease, recent studies have focused on the cellular mechanisms in brain inflammatory conditions that underlie AD neuropathology. Microglia are macrophage cells in the central nervous system that are activated in response to Aβ condition. The function of microglia contributes to the neuroinflammation in AD brain, suggesting that microglia regulate the production of inflammatory mediators and contribute to the regeneration of damaged tissues. Adiponectin, an adipokine derived from adipose tissue, has been known to regulate inflammation and control macrophages during oxidative stress conditions. In present study, we investigated whether adiponectin influences the polarization and function of microglia under Aβ toxicity by examining alterations of BV2 microglia function and polarization by Acrp30 (a globular form of adiponectin) treatment using reverse transcription PCR, western blotting, and immunofluorescence staining. Acrp30 promoted the induction of the M2 phenotype, and regulated the inflammatory responses through peroxisome proliferator-activated receptor (PPAR)-γ signaling under Aβ toxicity. In addition, Acrp30 boosted the capacity of Aβ scavenging in microglia. Taken together, we suggest that adiponectin may control the function of microglia by promoting anti-inflammatory responses through PPAR- γ signaling. Hence, we conclude that adiponectin may act as a critical controller of microglia function in the AD brain.

Alzheimer’s disease (AD) is the most common neurodegenerative disease, characterized by excessive beta amyloid (Aβ) deposition in brain, leading to blood–brain barrier (BBB) disruption. The mechanisms of BBB disruption in AD are still unclear, despite considerable research. The adipokine adiponectin is known to regulate various metabolic functions and reduce inflammation. Though adiponectin receptors have been reported in the brain, its role in the central nervous system has not been fully characterized. In the present study, we investigate whether adiponectin contributes to the tight junction integrity and cell death of brain endothelial cells under Aβ-induced toxicity conditions. We measured the expression of adiponectin receptors (AdipoR1 and AdipoR2) and the alteration of tight junction proteins in in vivo 5xFAD mouse brain. Moreover, we examined the production of reactive oxygen species (ROS) and the loss of tight junction proteins such as Claudin 5, ZO-1, and inflammatory signaling in in vitro brain endothelial cells (bEnd.3 cells) under Aβ toxicity. Our results showed that Acrp30 (a globular form of adiponectin) reduces the expression of proinflammatory cytokines and the expression of RAGE as Aβ transporters into brain. Moreover, we found that Acrp 30 attenuated the apoptosis and the tight junction disruption through AdipoR1-mediated NF-κB pathway in Aβ-exposed bEnd.3 cells. Thus, we suggest that adiponectin is an attractive therapeutic target for treating BBB breakdown in AD brain.

BACKGROUND AND PURPOSE: A major concern after emergent intracranial angioplasty in cases of acute stroke with underlying intracranial stenosis is the acute reocclusion of the treated arteries. This study reports the incidence and clinical outcomes of acute reocclusion of arteries following emergent intracranial angioplasty with or without stent placement for the management of patients with acute stroke with underlying intracranial atherosclerotic stenosis. MATERIALS AND METHODS: Forty-six patients with acute stroke received emergent intracranial angioplasty with or without stent placement for intracranial atherosclerotic stenosis and underwent follow-up head CTA. Acute reocclusion was defined as “hypoattenuation” within an arterial segment with discrete discontinuation of the arterial contrast column, both proximal and distal to the hypoattenuated lesion, on CTA performed before discharge. Angioplasty was defined as “suboptimal” if a residual stenosis of ≥50% was detected on the postprocedural angiography. Clinical and radiologic data of patients with and without reocclusion were compared. RESULTS: Of the 46 patients, 29 and 17 underwent angioplasty with and without stent placement, respectively. Acute reocclusion was observed in 6 patients (13%) and was more frequent among those with suboptimal angioplasty than among those without it (71.4% versus 2.6%, P < .001). The relative risk of acute reocclusion in patients with suboptimal angioplasty was 27.857 (95% confidence interval, 3.806–203.911). Furthermore, a good outcome was significantly less frequent in patients with acute reocclusion than in those without it (16.7% versus 67.5%, P = .028). CONCLUSIONS: Acute reocclusion of treated arteries was common after emergent intracranial angioplasty with or without stent placement in patients with acute stroke with intracranial atherosclerotic stenosis and was associated with a poor outcome. Suboptimal results of angioplasty appear to be associated with acute reocclusion, irrespective of whether stent placement was performed.