This study aims to explore the diagnosis in patients with Alzheimer's disease (AD) based on magnetic resonance (MR) images, and to compare the differences of bilateral hippocampus in classification and recognition. MR images were obtained from 25 AD patients and 25 normal controls (NC) respectively. Three-dimensional texture features were extracted from bilateral hippocampus of each subject. The texture features that existed significant differences between AD and NC were used as the features in a classification procedure. Back propagation (BP) neural network model was built to classify AD patients from healthy controls. The classification accuracy of three methods, which were principal components analysis, linear discriminant analysis and non-linear discriminant analysis, was obtained and compared. The correlations between bilateral hippocampal texture parameters and Mini-Mental State Examination (MMSE) scores were calculated. The classification accuracy of nonlinear discriminant analysis with a neural network model was the highest, and the classification accuracy of right hippocampus was higher than that of the left. The bilateral hippocampal texture features were correlated to MMSE scores, and the relative of right hippocampus was higher than that of the left. The neural network model with three-dimensional texture features could recognize AD patients and NC, and right hippocampus might be more helpful to AD diagnosis.
Objective
To observe the changes of retinal nerve fiber layer (RNFL) thickness in patients with Alzheimer's disease (AD).
Methods
Twenty eyes of 40 patients with mild and (or) moderate AD confirmed by clinical examination (AD group) were included in the study. There were 11 males and 9 females with an average age of (72.75±8.25) years. Age and gender-matched normal 20 objectives were in the normal control group. Among them, there were 11 males and 9 females with a mean age of (71.05±7.08) years. There was no significant difference in gender composition, age and intraocular pressure between the two groups (P＞0.05). There were significant differences in visual acuity, cup disc ratio and mini-mental state examination score (P＜0.05). All eyes underwent high-resolution optical coherence tomography (OCT) examination. With a diameter of 3.4 mm and a center on the center of the optic disc, circular fast scans on optic disc were performed to obtain an average disc RNFL thickness, signal threshold ＞6. Computer image analysis system was used to measure the RNFL thickness from superior, inferior, temporal and nasal quadrants, and the average RNFL thickness. The changes of RNFL thickness between the two groups and between different eyes of the same group were compared.
Results
Compared with the normal control group, the average (t=5.591), superior (t=8.169, 8.053) and inferior (t=12.596, 11.377) thickness of RNFL in both eyes in AD group were thinner, the differences were significant (P＜0.05); the temporal (t=1.966, 0.838）and nasal (t=2.071, 0.916) thickness of RNFL in both eyes of AD group were thinner, but the difference was not statistically significant (P＞0.05). There was no significant difference of the mean and different quadrant RNFL thickness between different eyes in AD group and normal control group (AD group: t=0.097, 0.821, 0.059, 0.020, 0.116; normal control group: t=0.791, 1.938, 1.806, 2.058, 1.005; P＞0.05).
Conclusion
The RNFL thickness around the optic disc in AD patients is thinner; This occurs first in superior and inferior quadrants of the optic disc.
With the exacerbation of aging population in China, the number of patients with Alzheimer's disease (AD) is increasing rapidly. AD is a chronic but irreversible neurodegenerative disease, which cannot be cured radically at present. In recent years, in order to intervene in the course of AD in advance, many researchers have explored how to detect AD as early as possible, which may be helpful for effective treatment of AD. Imaging genomics is a kind of diagnosis method developed in recent years, which combines the medical imaging and high-throughput genetic omics together. It studies changes in cognitive function in patients with AD by extracting effective information from high-throughput medical imaging data and genomic data, providing effective guidance for early detection and treatment of AD patients. In this paper, the association analysis of magnetic resonance image (MRI) with genetic variation are summarized, as well as the research progress on AD with this method. According to complexity, the objects in the association analysis are classified as candidate brain phenotype, candidate genetic variation, genome-wide genetic variation and whole brain voxel. Then we briefly describe the specific methods corresponding to phenotypic of the brain and genetic variation respectively. Finally, some unsolved problems such as phenotype selection and limited polymorphism of candidate genes are put forward.
Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder. Due to the subtlety of symptoms in the early stages of AD, rapid and accurate clinical diagnosis is challenging, leading to a high rate of misdiagnosis. Current research on early diagnosis of AD has not sufficiently focused on tracking the progression of the disease over an extended period in subjects. To address this issue, this paper proposes an ensemble model for assisting early diagnosis of AD that combines structural magnetic resonance imaging (sMRI) data from two time points with clinical information. The model employs a three-dimensional convolutional neural network (3DCNN) and twin neural network modules to extract features from the sMRI data of subjects at two time points, while a multi-layer perceptron (MLP) is used to model the clinical information of the subjects. The objective is to extract AD-related features from the multi-modal data of the subjects as much as possible, thereby enhancing the diagnostic performance of the ensemble model. Experimental results show that based on this model, the classification accuracy rate is 89% for differentiating AD patients from normal controls (NC), 88% for differentiating mild cognitive impairment converting to AD (MCIc) from NC, and 69% for distinguishing non-converting mild cognitive impairment (MCInc) from MCIc, confirming the effectiveness and efficiency of the proposed method for early diagnosis of AD, as well as its potential to play a supportive role in the clinical diagnosis of early Alzheimer's disease.
ObjectiveTo systematically review the correlation between apolipoprotein E (ApoE) polymorphism and sporadic Alzheimer's disease (SAD) in Chinese population.
MethodsThe case-control studies about the relationship between ApoE polymorphism and SAD in Chinese population were electronically retrieved in PubMed, EMbase, CBM, The Cochrane Library (Issue 8, 2013), CNKI, VIP, and WanFang Data from the date of their establishment to August 2013. Literature screening according to the inclusion and exclusion criteria, data extraction and methodological quality assessment of the included stuides were completed by two reviewers independently. Meta-analysis was then conducted using Stata 12.0 software.
ResultsA total of 50 case-control studies invovling 3 396 cases and 4 917 controls were finally included. The results of meta-analysis showed that, in Chinese, the risk of SAD was 2.89 times higher in population with allele ε4 than in population with allele ε3 (OR=2.89, 95%CI 2.61 to 3.19, P < 0.001); 7.24 times higher in those with ε4/ε4 genotype than in those with ε3/ε3 genotype (OR=7.24, 95%CI 5.11 to 10.24, P < 0.001); 2.90 times higher in ε3/ε4 genotype than in ε3/ε3 genotype (OR=2.90, 95%CI 2.56 to 3.29, P < 0.001); 2.11 times higher in ε2/ε4 genotype than in ε3/ε3 genotype (OR=2.11, 95%CI 1.64 to 2.72, P < 0.001); and no statistic significance was found in the risk of SAD compared ε2/ε3, ε2/ε2 genotypes and ε2 allele with ε3/ε3 genotype and ε3 allele.
ConclusionFor Chinese population, ApoE allele ε4 is significantly associated with the onset of SAD, and genotype ε4/ε4 is a high risk factor of SAD. While allele ε2 is not associated with the onset of SAD. Since a great deal of current studies failed to conduct stratified analysis, it is suggested to further conduct relevant relevant studies according to clinical classification of SAD and patients' characteristics.
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's disease is a common neuro-degenerative disease. The clinical diagnosis mainly depends on the patient's complaint, the score of mini-mental state examination and Montreal cognitive assessment scale, and the comprehensive judgment of MRI and other imaging examinations. Retina is homologous to brain tissue, and their vascular systems have similar physiological characteristics to small blood vessels in the brain. Numerous studies found that the thickness of retinal nerve fiber layer, visual function, retinal blood vessels and retinal oxygen saturation were changed in AD patients to different degrees. To explore the formation mechanism and significance of ocular fundus changes in AD patients will be helpful to select specific, sensitive and simple methods for early observation and evaluation of AD.
ObjectivesTo systematically review the efficacy of seven types of cognitive interventions for older adults with mild to moderate Alzheimer's Disease (AD).MethodsWe searched The Cochrane Library, PubMed, EMbase, CNKI, WanFang Data, VIP and CBM databases to collect randomized controlled trials on cognitive interventions for mild to moderate Alzheimer's Disease (AD) from inception to January 2018. Two reviewers independently screened literature, extracted data, and assessed the risk of bias of included studies. STATA 14.0 software was then used to perform a meta-analysis.ResultsA total of 49 randomized controlled trials (RCTs) were included. The results of network meta-analysis revealed that each cognitive intervention had significantly improved the cognitive ability of AD patients. Specifically, nursing intervention (NI) (MD=3.01, 95%CI 1.70 to 4.50, P<0.005) was the most effective enhancer of cognitive ability, followed by music therapy (MT) (MD=2.60, 95%CI 0.96 to 4.30, P<0.001), physical exercise (PE) (MD=2.4, 95%CI 1.0 to 3.9, P<0.001), cognitive rehabilitation (CR) (MD=2.3, 95% CI 0.92 to 3.7, P=0.013), cognitive simulation (CS) (MD=1.7, 95%CI 1.2 to 2.3, P=0.037), computerized cognitive training (CCT) (MD=1.6, 95%CI 0.42 to 2.8, P<0.001), and pharmacological therapies (PT) (MD=1.5, 95%CI 0.24 to 2.8, P=0.041).ConclusionsThe seven types of cognitive interventions are helpful in improving the cognitive ability of Alzheimer's patients, and nursing intervention is the most effective cognitive intervention. Moreover, non-pharmacological therapies may be better than pharmacological therapies.
Objective To systematically review the efficacy, safety, cost-effectiveness, indications, contraindications, and ethical issues for surgical treatment of Alzheimer's disease (AD). Methods The CNKI, WanFang Data, VIP, PubMed, Web of Science, Embase and Cochrane Library databases were electronically searched to collect for relevant studies on surgical treatment of AD from inception to November 26, 2024. Two reviewers independently screened literature, extracted data, and assessed the risk of bias of the included studies. Meta-analysis was performed by using Stata 17 software. Results A total of 59 studies were included. The results revealed that surgical treatment for AD had higher safety (OR=0.44, 95%CI 0.17 to 0.72, P<0.05), and patients had better ADAS-cog scores (SMD=0.54, 95%CI 0.18 to 0.90, P<0.05), with statistically significant differences. The economic burden of surgical treatment for AD increased with the severity of the disease. Deep brain stimulation may offer high economic benefits in the treatment of mild AD. The surgical indications can be summarized as: short disease duration, mild to moderate severity, and insufficient response to pharmacological interventions. Regarding contraindications, analysis of the included literature identified four core aspects: physiological and pathological contraindications, medical comorbidities and surgical risk contraindications, cognitive and psychological factor contraindications, and other contraindications. Ethical issues can be categorized into: informed consent and autonomy, ethical review and approval of research, and assessment of risks and benefits. Conclusion Current evidence suggests that surgical treatment for AD has certain benefits, but the surgical approaches for treating AD are still in the exploratory stage. Limited by the number and quality of the included studies, the above conclusion still requires more high-quality research to be verified.
Wavelet entropy is a quantitative index to describe the complexity of signals. Continuous wavelet transform method was employed to analyze the spontaneous electroencephalogram (EEG) signals of mild, moderate and severe Alzheimer's disease (AD) patients and normal elderly control people in this study. Wavelet power spectrums of EEG signals were calculated based on wavelet coefficients. Wavelet entropies of mild, moderate and severe AD patients were compared with those of normal controls. The correlation analysis between wavelet entropy and MMSE score was carried out. There existed significant difference on wavelet entropy among mild, moderate, severe AD patients and normal controls (P<0.01). Group comparisons showed that wavelet entropy for mild, moderate, severe AD patients was significantly lower than that for normal controls, which was related to the narrow distribution of their wavelet power spectrums. The statistical difference was significant (P<0.05). Further studies showed that the wavelet entropy of EEG and the MMSE score were significantly correlated (r=0.601-0.799, P<0.01). Wavelet entropy is a quantitative indicator describing the complexity of EEG signals. Wavelet entropy is likely to be an electrophysiological index for AD diagnosis and severity assessment.
