Diagnosis and Prognosis of Alzheimer?s Disease Via 3D CNN

Mild Cognitive Impairment (MCI) is an early symptom of Alzheimer’s disease (AD). The feature extraction and deep learning architecture of the convolutional neural network in 3D brain images is applied to the problem of Alzheimer’s disease. The Structural Magnetic Resonance (sMRI) and Positron Emission Tomography (PET) image of the patient’s brain are classified according to the vigorousness of the disease and is labelled to be either in MCI or in AD or Normal Control (NC) condition. In this paper, we proposed a model and presented the baseline convolutional CNN with four layers viz., Convolutional layer, Leaky Rectified Linear Unit(LReLU), S3Pool layer and Global average pooling. Further, the 3D image data is used to perform the binary and ternary classifications and its performance are examined. The strength of the network has improved interior resource utilization evaluated with medical images, sMRI and PET on hippocampal ROI. The results of our proposed CNN architecture have achieved an accuracy level of 0.945, 0.859 and 0.748 respectively, when compared to the conventional AlexNet based network. The obtained data from the ADNI database shows better performance with our proposed model.

Download Full-text

Anomaly Analysis of Alzheimer’s Disease in PET Images Using an Unsupervised Adversarial Deep Learning Model

Applied Sciences ◽

10.3390/app11052187 ◽

2021 ◽

Vol 11 (5) ◽

pp. 2187

Author(s):

Husnu Baris Baydargil ◽

Jang-Sik Park ◽

Do-Young Kang

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Area Under The Curve ◽

Qualitative Evaluation ◽

Input Image ◽

Normal Brain ◽

Brain Images ◽

Positron Emission ◽

Proposed Model ◽

Anomaly Analysis

In this study, the anomaly analysis of Alzheimer’s disease using positron emission tomography (PET) images using an unsupervised proposed adversarial model is investigated. The model consists of three parts: a parallel-network encoder, which is comprised of a convolutional pipeline and a dilated convolutional pipeline that extracts global and local features and concatenates them, a decoder that reconstructs the input image from the obtained feature vector, and a discriminator that distinguishes if the input image image is real or fake. The hypothesis is that if the proposed model is trained with only normal brain images, the corresponding construction loss for normal images should be minimal. However, if the input image belongs to a class that is designated as an anomaly that which the model is not trained with, then the construction loss will be high. This will reflect during the anomaly score comparison between the normal and the anomalous image. A multi-case analysis is performed for three major classes using the Alzheimer’s Disease Neuroimaging Initiative dataset, Alzheimer’s disease, mild cognitive impairment, and normal control. The base parallel-encoder network shows better classification accuracy than the benchmark models, and the proposed model that is built on the parallel model outperforms the benchmark anomaly detection models. The proposed model gave out 96.03% and 75.21% in classification and area under the curve score, respectively. Additionally, a qualitative evaluation done by using Fréchet inception distance gave a better score than the state-of-the-art by three points.

Download Full-text

Biomarkers for Alzheimer’s Disease Early Diagnosis

Journal of Personalized Medicine ◽

10.3390/jpm10030114 ◽

2020 ◽

Vol 10 (3) ◽

pp. 114 ◽

Cited By ~ 2

Author(s):

Eva Ausó ◽

Violeta Gómez-Vicente ◽

Gema Esquiva

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Neuronal Loss ◽

Diagnostic Tools ◽

Csf Biomarkers ◽

Diagnosis And Prognosis ◽

Positron Emission ◽

The Central Nervous System ◽

Magnetic Resonance Imaging Mri ◽

The Brain

Alzheimer’s disease (AD) is the most common cause of dementia, affecting the central nervous system (CNS) through the accumulation of intraneuronal neurofibrillary tau tangles (NFTs) and β-amyloid plaques. By the time AD is clinically diagnosed, neuronal loss has already occurred in many brain and retinal regions. Therefore, the availability of early and reliable diagnosis markers of the disease would allow its detection and taking preventive measures to avoid neuronal loss. Current diagnostic tools in the brain, such as magnetic resonance imaging (MRI), positron emission tomography (PET) imaging, and cerebrospinal fluid (CSF) biomarkers (Aβ and tau) detection are invasive and expensive. Brain-secreted extracellular vesicles (BEVs) isolated from peripheral blood have emerged as novel strategies in the study of AD, with enormous potential as a diagnostic evaluation of therapeutics and treatment tools. In addition; similar mechanisms of neurodegeneration have been demonstrated in the brain and the eyes of AD patients. Since the eyes are more accessible than the brain, several eye tests that detect cellular and vascular changes in the retina have also been proposed as potential screening biomarkers. The aim of this study is to summarize and discuss several potential markers in the brain, eye, blood, and other accessible biofluids like saliva and urine, and correlate them with earlier diagnosis and prognosis to identify individuals with mild symptoms prior to dementia.

Download Full-text

The Potential Use of Blood, Cerebrospinal Fluid, Saliva and Urine as Biological Samples for the Diagnosis of Alzheimer’s Disease

International Journal of Biochemistry Research & Review ◽

10.9734/ijbcrr/2020/v29i830210 ◽

2020 ◽

pp. 26-41

Author(s):

Adnan Awn Algarni ◽

Abdulhadi I. Bima ◽

Ayman Z. Elsamanoudy

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Cerebrospinal Fluid ◽

Biological Samples ◽

High Sensitivity ◽

High Specificity ◽

Clinical Criteria ◽

Diagnosis And Prognosis ◽

Positron Emission ◽

Potential Use

Background and Aim: Alzheimer’s disease (AD) is the most common cause of dementia. 80% of all dementia is due to AD. Diagnosis of AD is a difficult task, as the accurate diagnosis requires post-mortem examination of brain autopsy samples. Diagnosis of AD in living individuals can be aided by the establishment of the clinical criteria, positron emission tomography (PET) examination, and biomarkers. The study of biomarkers for diagnosis of AD could help clinicians to evaluate individuals at risk, and confirm the occurrence as well as the progression of AD in a non-invasive manner. High sensitivity and high specificity of the used markers are mandatory criteria for these biomarkers to trusted for AD diagnosis and prognosis. So, this review article aims to focus on the potential use of body fluids as a source of the biomarkers that are used for investigating patients with AD. Methodology: In the current study, we reviewed scientific articles that discuss AD pathogenesis and diagnosis of Google Scholar database, Pubmed, Pubmed Central, Cochrane Database of Systematic Reviews (CDSR), MEDLINE, and MedlinePlus with no time limitation. Moreover, we discussed the use of recently discovered biomarkers that are detected in blood, CSF, saliva, and urine. Conclusion: In the current review, it could be concluded that in addition to the blood and cerebrospinal fluid as common biological samples for the diagnosis of AD, saliva and urine are useful potential biological samples. Moreover, both are noninvasive samples that give them priority to be used.

Download Full-text