No abstract

Purpose: To perform automatic assessment of dementia severity using a deep learning framework applied to resting-state functional magnetic resonance imaging (rs-fMRI) data.Method: We divided 133 Alzheimer’s disease (AD) patients with clinical dementia rating (CDR) scores from 0.5 to 3 into two groups based on dementia severity; the groups with very mild/mild (CDR: 0.5–1) and moderate to severe (CDR: 2–3) dementia consisted of 77 and 56 subjects, respectively. We used rs-fMRI to extract functional connectivity features, calculated using independent component analysis (ICA), and performed automated severity classification with three-dimensional convolutional neural networks (3D-CNNs) based on deep learning.Results: The mean balanced classification accuracy was 0.923 ± 0.042 (p < 0.001) with a specificity of 0.946 ± 0.019 and sensitivity of 0.896 ± 0.077. The rs-fMRI data indicated that the medial frontal, sensorimotor, executive control, dorsal attention, and visual related networks mainly correlated with dementia severity.Conclusions: Our CDR-based novel classification using rs-fMRI is an acceptable objective severity indicator. In the absence of trained neuropsychologists, dementia severity can be objectively and accurately classified using a 3D-deep learning framework with rs-fMRI independent components.

Background Early diagnosis of Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this paper, we propose a voxel-wise discriminative framework applied to multi-measure resting-state fMRI (rs-fMRI) that integrates hybrid MVPA and extreme learning machine (ELM) for the automated discrimination of AD and MCI from the cognitive normal (CN) state. Materials and methods We used two rs-fMRI cohorts: the public Alzheimer’s disease Neuroimaging Initiative database (ADNI2) and an in-house Alzheimer’s disease cohort from South Korea, both including individuals with AD, MCI, and normal controls. After extracting three-dimensional (3-D) patterns measuring regional coherence and functional connectivity during the resting state, we performed univariate statistical t-tests to generate a 3-D mask that retained only voxels showing significant changes. Given the initial univariate features, to enhance discriminative patterns, we implemented MVPA feature reduction using support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO), in combination with the univariate t-test. Classifications were performed by an ELM, and its efficiency was compared to linear and nonlinear (radial basis function) SVMs. Results The maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p<0.001) and 98.57% (p<0.001) for AD and MCI vs. CN, respectively. In the in-house cohort, the same accuracies were 98.70% (p<0.001) and 94.16% (p<0.001). Conclusion From a clinical perspective, combining extreme learning machine and hybrid MVPA applied on concatenations of multiple rs-fMRI biomarkers can potentially assist the clinicians in AD and MCI diagnosis.

IntroductionThe accumulation of amyloid-beta (Aβ) is one of the neuropathologic hallmarks of Alzheimer’s disease (AD) and abnormal gamma band oscillations and brain connectivity have been observed. Recently, a therapeutic potential of gamma entrainment of the brain was reported by Iaccarino et al. However, the affected areas were limited to hippocampus and visual cortex. Therefore, we sought to test the effects of acoustic stimulation in a mouse model of AD.MethodsFreely moving 6-month-old 5XFAD mice with electroencephalogram (EEG) electrodes were treated with daily two-hour acoustic stimulation at 40Hz for 2 weeks. Aβ and microglia were evaluated by immunohistochemistry and ELISA. Evoked and spontaneous gamma power were analyzed by wavelet analysis. Coherence, phase locking value (PLV), and cross-frequency coupling were analyzed.ResultsThe number of Aβ plaques decreased in the pre-and infralimbic (PIL) and hippocampus regions and soluble Aβ-40 and Aβ-42 peptides in PIL in the acoustic stimulation group. We also found that the number of microglia increased in PIL and hippocampus. In EEG analysis, evoked gamma power was decreased and spontaneous gamma power was increased. Gamma coherence and phase locking value did not show significant changes. Cross-frequency coupling was shifted from gamma-delta to gamma-theta rhythm.ConclusionIn summary, we found that acoustic stimulation at 40Hz can reduce Aβ in the brain and restore the gamma band oscillations and the frontoparietal connectivity. Our data suggest that acoustic stimulation might alter the natural deterioration processes of AD and have a therapeutic potential in AD.

clozapine (cLZ) has been proposed as an agonist for Designer Receptors exclusively Activated by Designer Drugs (DREADDs), to replace Clozapine-N-oxide (CNO); however, there are no reliable guidelines for the use of cLZ for chemogenetic neuromodulation. We titrated the optimal dose of cLZ required to evoke changes in neural activity whilst avoiding off-target effects. We also performed [ 18 f] fluoro-deoxy-glucose micro positron emission tomography (fDG-micropet) scans to determine the global effect of CLZ-induced hM3D(Gq) DREADD activation in the rat brain. Our results show that low doses of CLZ (0.1 and 0.01 mg/kg) successfully induced neural responses without off-target effects. CLZ at 1 mg/kg evoked a stronger and longer-lasting neural response but produced off-target effects, observed as changes in locomotor behavior and FDG-microPET imaging. Unexpectedly, FDG-microPET imaging failed to demonstrate an increase in regional glucose metabolism in the stimulated cortex during CLZ chemogenetic neuromodulation. Therefore, caution should be used when interpreting FDGpet images in the context of cortical chemogenetic activation.