scholarly journals Automated Multimodal Fusion Technique for the Classification of Human Brain on Alzheimer’s Disorder

2021 ◽  
Vol 3 (3) ◽  
pp. 214-229
Author(s):  
B. Vivekanandam
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Performance Metrics ◽  
Research Output ◽  
Hybrid Approach ◽  
Disease Diagnosis ◽  
Great Accuracy ◽  
Multimodal Fusion ◽  
Research Article ◽  
Mri Characteristics

Alzheimer's Disorder (AD) may permanently impair memory cells, resulting in dementia. Researchers say that early Alzheimer's disease diagnosis is difficult. MRI is used to detect AD in clinical trials. It requires high discriminative MRI characteristics to accurately classify dementia stages. Due to the large extraction of features, improved deep CNN-based models have recently proven accurate. With fewer picture samples in the datasets, over-fitting issues arise, limiting the effectiveness of deep learning algorithms. This research article minimizes the overfitting error due to fusion techniques. This hybrid approach is used to classify Alzheimer's disease more accurately than other traditional approaches. Besides, the Convolutional Neural Network (CNN) provides more minute features of small changes in MRI scan images than any other algorithm. Therefore, the proposed algorithm provides great accuracy in the region of sagittal, coronal, and axial Mild Cognitive Impairments (MCI) in the brain segment classification. Moreover, this research article compares the proposed algorithm with previous research output that is used to help prove its superiority. The performance metrics uses Health Subject (HS), MCI, and Mini-Mental State Evaluation (MMSE) to evaluate the proposed research algorithm.

scholarly journals An Effective Multimodal Image Fusion Method Using MRI and PET for Alzheimer's Disease Diagnosis

2021 ◽  
Vol 3 ◽  
Author(s):  
Juan Song ◽  
Jian Zheng ◽  
Ping Li ◽  
Xiaoyuan Lu ◽  
Guangming Zhu ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Image Fusion ◽  
Fdg Pet ◽  
Feature Fusion ◽  
Brain Mri ◽  
Disease Diagnosis ◽  
Multimodal Fusion ◽  
Fusion Method ◽  
Image Fusion Method

Alzheimer's disease (AD) is an irreversible brain disease that severely damages human thinking and memory. Early diagnosis plays an important part in the prevention and treatment of AD. Neuroimaging-based computer-aided diagnosis (CAD) has shown that deep learning methods using multimodal images are beneficial to guide AD detection. In recent years, many methods based on multimodal feature learning have been proposed to extract and fuse latent representation information from different neuroimaging modalities including magnetic resonance imaging (MRI) and 18-fluorodeoxyglucose positron emission tomography (FDG-PET). However, these methods lack the interpretability required to clearly explain the specific meaning of the extracted information. To make the multimodal fusion process more persuasive, we propose an image fusion method to aid AD diagnosis. Specifically, we fuse the gray matter (GM) tissue area of brain MRI and FDG-PET images by registration and mask coding to obtain a new fused modality called “GM-PET.” The resulting single composite image emphasizes the GM area that is critical for AD diagnosis, while retaining both the contour and metabolic characteristics of the subject's brain tissue. In addition, we use the three-dimensional simple convolutional neural network (3D Simple CNN) and 3D Multi-Scale CNN to evaluate the effectiveness of our image fusion method in binary classification and multi-classification tasks. Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset indicate that the proposed image fusion method achieves better overall performance than unimodal and feature fusion methods, and that it outperforms state-of-the-art methods for AD diagnosis.

Identification of a Pathogenic PSEN1 Ala285Val Mutation Associated with Early-Onset Alzheimer’s Disease

2020 ◽  
Vol 17 (5) ◽  
pp. 438-445
Author(s):  
Van Giau Vo ◽  
Jung-Min Pyun ◽  
Eva Bagyinszky ◽  
Seong S.A. An ◽  
Sang Y. Kim
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Temporal Lobe ◽  
Early Onset ◽  
Parietal Lobe ◽  
Disease Diagnosis ◽  
Random Coil ◽  
Magnetic Resonance Imaging Scan ◽  
Preclinical Ad ◽  
Early Onset Alzheimer’S Disease

Background: Presenilin 1 (PSEN1) was suggested as the most common causative gene of early onset Alzheimer’s Disease (AD). Methods: Patient who presented progressive memory decline in her 40s was enrolled in this study. A broad battery of neuropsychological tests and neuroimaging was applied to make the diagnosis. Genetic tests were performed in the patient to evaluate possible mutations using whole exome sequencing. The pathogenic nature of missense mutation and its 3D protein structure prediction were performed by in silico prediction programs. Results: A pathogenic mutation in PSEN1 (NM_000021.3: c.1027T>C p.Ala285Val), which was found in a Korean EOAD patient. Magnetic resonance imaging scan showed mild left temporal lobe atrophy. Hypometabolism appeared through 18F-fludeoxyglucose Positron Emission Tomography (FDG-PET) scanning in bilateral temporal and parietal lobe, and 18F-Florbetaben-PET (FBB-PET) showed increased amyloid deposition in bilateral frontal, parietal, temporal lobe and hence presumed preclinical AD. Protein modeling showed that the p.Ala285Val is located in the random coil region and could result in extra stress in this region, resulting in the replacement of an alanine residue with a valine. This prediction was confirmed previous in vitro studies that the p.Trp165Cys resulted in an elevated Aβ42/Aβ40 ratio in both COS-1 and HEK293 cell lines compared that of wild-type control. Conclusion: Together, the clinical characteristics and the effect of the mutation would facilitate our understanding of PSEN1 in AD pathogenesis for the disease diagnosis and treatment. Future in vivo study is needed to evaluate the role of PSEN1 p.Ala285Val mutation in AD progression.

A retrospective, population-based cohort study of driving under the influence, Alzheimer’s disease diagnosis, and survival

2018 ◽  
Vol 31 (04) ◽  
pp. 571-577 ◽  
Author(s):  
Margaret Miller ◽  
Dennis Orwat ◽  
Gelareh Rahimi ◽  
Jacobo Mintzer
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cohort Study ◽  
Law Enforcement ◽  
Disease Diagnosis ◽  
Population Based ◽  
Alcohol Addiction ◽  
Driving Under The Influence ◽  
History Of ◽  
The Relationship

ABSTRACTIntroduction:The relationship between Alzheimer’s Disease (AD) and alcohol addiction is poorly characterized. Arrests for driving under the influence (DUI) can serve as a proxy for alcohol addiction. Therefore, the potential association between DUI and AD could be helpful in understanding the relationship between alcohol abuse and AD.Materials and methods:A retrospective, population-based cohort study using state health and law enforcement data was performed. The study cross-referenced 141,281 South Carolina Alzheimer’s Disease Registry cases with state law enforcement data.Results:Of the 2,882 registry cases (1.4%) found to have a history of at least one DUI arrest, cases were predominantly White (58.7%) and male (77.4%). Results showed a correlation coefficient of 0.7 (p < 0.0001) between the age of first DUI arrest and the age of AD diagnosis. A dose-response relationship between the number of DUIs and age of AD onset was found to exist, where those with a history of DUI arrest were diagnosed an average of 9.1 years earlier, with a further 1.8 years earlier age at diagnosis in those with two or more arrests for DUI. A history of DUI arrest was also found to be negatively associated with survival after diagnosis, with a 10% decreased life expectancy in those with a DUI arrest history.Conclusions:Driving under the influence, a potential indicator of alcohol addiction, is associated with an earlier onset of AD registry diagnosis and shortened survival after diagnosis. This study contributes to the growing body of evidence suggesting that some cases of AD are alcohol related and, possibly, postponable or preventable.

Sign in / Sign up

Export Citation Format

Share Document