Alzheimer's disease (AD) is associated with the impairment of white matter (WM) tracts. The current study aimed to verify the utility of WM as the neuroimaging marker of AD with multisite diffusion tensor imaging datasets [321 patients with AD, 265 patients with mild cognitive impairment (MCI), 279 normal controls (NC)], a unified pipeline, and independent site cross-validation. Automated fiber quantification was used to extract diffusion profiles along tracts. Random-effects meta-analyses showed a reproducible degeneration pattern in which fractional anisotropy significantly decreased in the AD and MCI groups compared with NC. Machine learning models using tract-based features showed good generalizability among independent site cross-validation. The diffusion metrics of the altered regions and the AD probability predicted by the models were highly correlated with cognitive ability in the AD and MCI groups. We highlighted the reproducibility and generalizability of the degeneration pattern of WM tracts in AD.
Humans ; White Matter/diagnostic imaging* ; Diffusion Tensor Imaging/methods* ; Alzheimer Disease/complications* ; Reproducibility of Results ; Cognition ; Cognitive Dysfunction/complications* ; Brain/diagnostic imaging*

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. Neuroimaging based on magnetic resonance imaging (MRI) is one of the most intuitive and reliable methods to perform AD screening and diagnosis. Clinical head MRI detection generates multimodal image data, and to solve the problem of multimodal MRI processing and information fusion, this paper proposes a structural and functional MRI feature extraction and fusion method based on generalized convolutional neural networks (gCNN). The method includes a three-dimensional residual U-shaped network based on hybrid attention mechanism (3D HA-ResUNet) for feature representation and classification for structural MRI, and a U-shaped graph convolutional neural network (U-GCN) for node feature representation and classification of brain functional networks for functional MRI. Based on the fusion of the two types of image features, the optimal feature subset is selected based on discrete binary particle swarm optimization, and the prediction results are output by a machine learning classifier. The validation results of multimodal dataset from the AD Neuroimaging Initiative (ADNI) open-source database show that the proposed models have superior performance in their respective data domains. The gCNN framework combines the advantages of these two models and further improves the performance of the methods using single-modal MRI, improving the classification accuracy and sensitivity by 5.56% and 11.11%, respectively. In conclusion, the gCNN-based multimodal MRI classification method proposed in this paper can provide a technical basis for the auxiliary diagnosis of Alzheimer's disease.
Humans ; Alzheimer Disease/diagnostic imaging* ; Neurodegenerative Diseases ; Magnetic Resonance Imaging/methods* ; Neural Networks, Computer ; Neuroimaging/methods* ; Cognitive Dysfunction/diagnosis*

Diagnosis of Alzheimer dementia is done clinically using criteria set by different neurological associations. Inevitably, clinicians encounter cases that do not fulfill the set definitions and have to resort to supporting data to form a clinical judgment. Part of the ancillary work-up for dementia is the brain amyloid PET scan that has recently been available in the Philippines. It involves a radiopharmaceutical with high-affinity binding to amyloid plaques which for a time were thought to be central pathological finding for Alzheimer dementia. This study describes the first four amyloid PET scans in the Philippines and detail the protocol as well as interpretation of such studies. The procedure is not as simple and reproducible as one might think hence following the recommended protocol and interpretation guidelines are of utmost importance. We recommend standardization of the reporting of results for all centers that will cater to patients being worked up for dementia, which include reporting SUVRs for both whole cerebellum and cerebellar cortex. More studies are recommended to generate a local Florbetaben SUVR cutoff.
Alzheimer Disease ; Diagnostic Imaging

OBJECTIVES: To analyze the effect of acupuncture at the acupoints for Yizhi Tiaoshen (benefiting the intelligence and regulating the spirit) on the functional connectivity between the hippocampus and the whole brain in the patients with Alzheimer's disease (AD), and reveal the brain function mechanism of acupuncture in treatment of AD using resting state functional magnetic resonance imaging (rs-fMRI). METHODS: Sixty patients with mild to moderate AD were randomly divided into an acupuncture + medication group (30 cases, 3 cases dropped out) and a western medication group (30 cases, 2 cases dropped out). In the western medication group, the donepezil hydrochloride tablets were administered orally, 2.5 mg to 5 mg each time, once daily; and adjusted to be 10 mg each time after 4 weeks of medication. Besides the therapy as the western medication group, in the acupuncture + medication group, acupuncture was supplemented at the acupoints for Yizhi Tiaoshen, i.e. Baihui (GV 20), Sishencong (EX-HN 1), and bilateral Shenmen (HT 7), Neiguan (PC 6), Zusanli (ST 36), Sanyinjiao (SP 6) and Xuanzhong (GB 39). The needles were retained for 30 min in one treatment, once daily; and 6 treatments were required weekly. The duration of treatment was 6 weeks in each group. The general cognitive function was assessed by the mini-mental state examination (MMSE) and Alzheimer's disease assessment scale-cognitive part (ADAS-Cog) before and after treatment in the two groups. Using the rs-fMRI, the changes in the functional connectivity (FC) of the left hippocampus and the whole brain before and after treatment were analyzed in the patients of the two groups (11 cases in the acupuncture + medication group and 12 cases in the western medication group). RESULTS: After treatment, compared with those before treatment, MMSE scores increased and ADAS-Cog scores decreased in the two groups (P<0.05); MMSE score was higher, while the ADAS-Cog score was lower in the acupuncture + medication group when compared with those in the western medication group (P≤0.05). After treatment, in the western medication group, FC of the left hippocampus was enhanced with the left fusiform gyrus, the inferior frontal gyrus of the left triangular region, the bilateral superior temporal gyrus and the right superior parietal gyrus (P<0.05), while FC was weakened with the left inferior temporal gyrus, the left middle frontal gyrus and the right dorsolateral superior frontal gyrus when compared with that before treatment (P<0.05). After treatment, in the acupuncture + medication group, FC of the left hippocampus was increased with the right gyrus rectus, the left inferior occipital gyrus, the right superior temporal gyrus and the left middle occipital gyrus (P<0.05), and it was declined with the left thalamus (P<0.05) when compared with those before treatment. After treatment, in the acupuncture + medication group, FC of the left hippocampus was strengthened with the bilateral inferior temporal gyrus, the bilateral middle temporal gyrus, the right gyrus rectus, the bilateral superior occipital gyrus, the left lenticular nucleus putamen, the left calcarine fissure and surrounding cortex, the inferior frontal gyrus of the left insulae operculum, the left medial superior frontal gyrus and the right posterior central gyrus (P<0.05) compared with that of the western medication group. CONCLUSIONS Acupuncture at the acupoints for Yizhi Tiaoshen improves the cognitive function of AD patients, and its main brain functional mechanism is related to intensifying the functional connectivity of the left hippocampus with the default network (inferior temporal gyrus, middle temporal gyrus and superior frontal gyrus, gyrus rectus), as well as with the sensory (posterior central gyrus) and visual (calcarine fissure and surrounding cortex and superior occipital gyrus) brain regions.
Humans ; Acupuncture Points ; Alzheimer Disease/therapy* ; Magnetic Resonance Imaging ; Brain/physiology* ; Acupuncture Therapy ; Hippocampus/diagnostic imaging*

Objective To investigate the brain age differences between Alzheimer's disease(AD)and mild cognitive impairment(MCI)patients,and further explore the correlations between brain age gap(BAG)and clinical features.Methods The clinical data and radiologic findings of 132 probable AD and AD-derived MCI patients diagnosed at Beijing Tiantan Hospital,Capital Medical University from December 2018 to July 2021 were retrospectively analyzed.According to the diagnostic criteria for AD and MCI,the patients were assigned into AD and MCI groups.In addition,156 volunteers without neurological diseases and other severe diseases were recruited as the control group.The general data,Montreal cognitive assessment(MoCA)score,and mini-mental state examination(MMSE)score were compared among the three groups.The deep learning-based brain age prediction model was employed to calculate the BAGs of the three groups.Spearman correlation analysis was conducted to explore the correlations between BAG and clinical features.Results The 132 patients included 106 patients in the AD group and 26 patients in the MCI group.The MoCA and MMSE scores followed an ascending trend of AD groupP<0.001).The predicted brain age and BAG in the AD group were higher than those in the MCI group(P=0.040,P=0.003)and control group(P=0.001,P<0.001).There was no significant difference in predicted brain age or BAG between MCI and control groups(P=0.352,P=0.224).BAG was negatively correlated with MoCA score(r=-0.341,P<0.001)and MMSE score(r=-0.324,P=0.001)in the AD group.Conclusion BAG can be used as an imaging biomarker to evaluate the degree of brain structural variation and the severity of brain injury in the patients with cognitive impairment.
Humans ; Alzheimer Disease ; Retrospective Studies ; Cognitive Dysfunction ; Brain/diagnostic imaging*

Alzheimer's disease (AD) is an irreversible neurodegenerative disorder that damages patients' memory and cognitive abilities. Therefore, the diagnosis of AD holds significant importance. The interactions between regions of interest (ROIs) in the brain often involve multiple areas collaborating in a nonlinear manner. Leveraging these nonlinear higher-order interaction features to their fullest potential contributes to enhancing the accuracy of AD diagnosis. To address this, a framework combining nonlinear higher-order feature extraction and three-dimensional (3D) hypergraph neural networks is proposed for computer-assisted diagnosis of AD. First, a support vector machine regression model based on the radial basis function kernel was trained on ROI data to obtain a base estimator. Then, a recursive feature elimination algorithm based on the base estimator was applied to extract nonlinear higher-order features from functional magnetic resonance imaging (fMRI) data. These features were subsequently constructed into a hypergraph, leveraging the complex interactions captured in the data. Finally, a four-dimensional (4D) spatiotemporal hypergraph convolutional neural network model was constructed based on the fMRI data for classification. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database demonstrated that the proposed framework outperformed the Hyper Graph Convolutional Network (HyperGCN) framework by 8% and traditional two-dimensional (2D) linear feature extraction methods by 12% in the AD/normal control (NC) classification task. In conclusion, this framework demonstrates an improvement in AD classification compared to mainstream deep learning methods, providing valuable evidence for computer-assisted diagnosis of AD.
Humans ; Alzheimer Disease/diagnostic imaging* ; Neural Networks, Computer ; Magnetic Resonance Imaging/methods* ; Neuroimaging/methods* ; Diagnosis, Computer-Assisted ; Brain ; Cognitive Dysfunction

Alzheimer Disease ; Brain ; Humans ; White Matter/diagnostic imaging*

The pathogenesis of Alzheimer's disease (AD), a common neurodegenerative disease, is still unknown. It is difficult to determine the atrophy areas, especially for patients with mild cognitive impairment (MCI) at different stages of AD, which results in a low diagnostic rate. Therefore, an early diagnosis model of AD based on 3-dimensional convolutional neural network (3DCNN) and genetic algorithm (GA) was proposed. Firstly, the 3DCNN was used to train a base classifier for each region of interest (ROI). And then, the optimal combination of the base classifiers was determined with the GA. Finally, the ensemble consisting of the chosen base classifiers was employed to make a diagnosis for a patient and the brain regions with significant classification capability were decided. The experimental results showed that the classification accuracy was 88.6% for AD
Alzheimer Disease/diagnosis* ; Brain/diagnostic imaging* ; Cognitive Dysfunction/diagnosis* ; Early Diagnosis ; Humans ; Magnetic Resonance Imaging ; Neural Networks, Computer ; Neurodegenerative Diseases

With the wide application of deep learning technology in disease diagnosis, especially the outstanding performance of convolutional neural network (CNN) in computer vision and image processing, more and more studies have proposed to use this algorithm to achieve the classification of Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal cognition (CN). This article systematically reviews the application progress of several classic convolutional neural network models in brain image analysis and diagnosis at different stages of Alzheimer's disease, and discusses the existing problems and gives the possible development directions in order to provide some references.
Alzheimer Disease/diagnostic imaging* ; Cognitive Dysfunction/diagnosis* ; Humans ; Image Processing, Computer-Assisted ; Magnetic Resonance Imaging ; Neural Networks, Computer

OBJECTIVE: To propose a coupled convolutional and graph convolutional network (CCGCN) model for diagnosis of Alzheimer's disease (AD) and its prodromal stage. METHODS: The disease-related brain regions generated by group-wise comparison were used as the input. The convolutional neural networks (CNNs) were used to extract disease-related features from different locations on brain magnetic resonance (MR) images. The generated features via the graph convolutional network (GCN) were processed, and graph pooling was performed to analyze the inherent relationship between the brain topology and the diagnosis task adaptively. Through ADNI dataset, we acquired the accuracy, sensitivity and specificity of the diagnosis tasks for AD and its prodromal stages, followed by an ablation study on the model structure. RESULTS: The CCGCN model outperformed the current state-of-the-art methods and showed a classification accuracy of 92.5% for AD with a sensitivity of 88.1% and a specificity of 96.0%. CONCLUSIONS Based on the structural and topological features of the brain MR images, the proposed CCGCN model shows excellent performance in AD diagnosis and is expected to provide important assistance to physicians in disease diagnosis.
Alzheimer Disease ; diagnostic imaging ; Brain ; Humans ; Magnetic Resonance Imaging ; Neural Networks, Computer