$$\mathcal {B}\text {rain}{\mathcal{M}\mathcal{N}}\text {et}$$: a unified neural network architecture for brain image classification

Network Modeling Analysis in Health Informatics and Bioinformatics, Journal Year: 2024, Volume and Issue: 13(1)

Published: March 22, 2024

Language: Английский

---

Alzheimer’s disease detection and stage identification from magnetic resonance brain images using vision transformer

Machine Learning Science and Technology, Journal Year: 2024, Volume and Issue: 5(3), P. 035011 - 035011

Published: July 16, 2024

Abstract Machine learning techniques applied in neuroimaging have prompted researchers to build models for early diagnosis of brain illnesses such as Alzheimer’s disease (AD). Although this task is difficult, advanced deep-learning (DL) approaches can be used. These DL are effective, but difficult interpret, time-consuming, and resource-intensive. Therefore, neuroscientists interested employing novel, less complex structures transformers that superior pattern-extraction capabilities. In study, an automated framework accurate AD precise stage identification was developed by vision (ViTs) with fewer computational resources. ViT, which captures the global context opposed convolutional neural networks (CNNs) local receptive fields, more efficient image processing than CNN because a highly network connected parts. The self-attention mechanism ViT helps achieve goal. Magnetic resonance images belonging four stages were utilized develop proposed model, achieved 99.83% detection accuracy, 99.69% sensitivity, 99.88% specificity, 0.17% misclassification rate. Moreover, prove ability model generalize, mean distances transformer blocks attention heat maps visualized understand what learned from MRI input image.

Language: Английский

---

A Feature-Fusion Technique-Based Alzheimer’s Disease Classification Using Magnetic Resonance Imaging

Diagnostics, Journal Year: 2024, Volume and Issue: 14(21), P. 2363 - 2363

Published: Oct. 23, 2024

Early identification of Alzheimer's disease (AD) is essential for optimal treatment and management. Deep learning (DL) technologies, including convolutional neural networks (CNNs) vision transformers (ViTs) can provide promising outcomes in AD diagnosis. However, these technologies lack model interpretability demand substantial computational resources, causing challenges the resource-constrained environment. Hybrid ViTs outperform individual by visualizing key features with limited power. This synergy enhances feature extraction promotes interpretability.

Language: Английский

---

Analyzing subcortical structures in Alzheimer's disease using ensemble learning

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 87, P. 105407 - 105407

Published: Sept. 21, 2023

Language: Английский

---

Genetic algorithm-based hybrid deep learning model for explainable Alzheimer’s disease prediction using temporal multimodal cognitive data

International Journal of Data Science and Analytics, Journal Year: 2024, Volume and Issue: unknown

Published: March 8, 2024

Language: Английский

---

Development of a robust parallel and multi-composite machine learning model for improved diagnosis of Alzheimer's disease: correlation with dementia-associated drug usage and AT(N) protein biomarkers

Frontiers in Neuroscience, Journal Year: 2024, Volume and Issue: 18

Published: Sept. 6, 2024

Machine learning (ML) algorithms and statistical modeling offer a potential solution to offset the challenge of diagnosing early Alzheimer's disease (AD) by leveraging multiple data sources combining information on neuropsychological, genetic, biomarker indicators. Among others, models are promising tool enhance clinical detection AD. In present study, AD was diagnosed taking into account characteristics related whether or not patient specific drugs significant protein as predictor Amyloid-Beta (Aβ), tau, ptau [AT(N)] levels among participants.

Language: Английский

---

A Novel Method for Diagnosing Alzheimer’s Disease from MRI Scans using the ResNet50 Feature Extractor and the SVM Classifier

International Journal of Advanced Computer Science and Applications, Journal Year: 2023, Volume and Issue: 14(6)

Published: Jan. 1, 2023

Alzheimer's disease (AD), a chronic neurodegenerative brain disorder, caused by the accumulation of abnormal proteins called amyloid, is one prominent causes mortality worldwide. Since there scarcity experienced neurologists, manual diagnosis AD very time-consuming and error-prone. Hence, automatic draws significant attention nowadays. Machine learning (ML) algorithms such as deep are widely used to support early from magnetic resonance imaging (MRI). However, they provide better accuracy in binary classification, which not case with multi-class classification. On other hand, consists number stages, accurate detection them necessary. this research focuses on how multi-stage classification particularly its stage. After MRI scans have been preprocessed (through median filtering watershed segmentation), benchmark pre-trained convolutional neural network (CNN) models (AlexNet, VGG16, VGG19, ResNet18, ResNet50) carry out feature extraction. Then, principal component analysis optimize features. Conventional machine classifiers (Decision Tree, K-Nearest Neighbors, Support Vector Machine, Linear Programming Boost, Total Boost) deployed using optimized features for staging AD. We exploited Neuroimaging Initiative(ADNI) data set consisting AD, MCIs (MCI), cognitive normal (CN) classes images. In our experiment, SVM classifier performed extracted ResNet50 features, achieving 99.78% during training, 99.52% validation, 98.71% testing. Our approach distinctive because it combines advantages extractors, conventional classifiers, optimization.

Language: Английский

---

Identification of disease-specific bio-markers through network-based analysis of gene co-expression: A case study on Alzheimer's disease

Heliyon, Journal Year: 2024, Volume and Issue: 10(5), P. e27070 - e27070

Published: March 1, 2024

Finding biomarker genes for complex diseases attracts persistent attention due to its application in clinics. In this paper, we propose a network-based method obtain set of genes. The key idea is construct gene co-expression network among sensitive and cluster the into different modules. For each module, can identify representative, i.e., with largest connectivity smallest average shortest path length other within module. We believe these representative could serve as new potential biomarkers diseases. As typical example, investigated Alzheimer's disease, obtaining total 16 genes, three which belong non-transcriptome. A 11 out are found literature from perspectives methods. incipient groups were classified two subtypes using machine learning algorithms. subjected Gene Ontology analysis Kyoto Encyclopedia Genes Genomes healthy moderate groups, respectively. sub-type involved biological processes, demonstrating validity approach. This disease-specific independent; hence, it be extended classify kinds

Language: Английский

---

Alzheimer's Dementia and its Various Biomarker Details with Several Detection Methodologies - A Comprehensive Review

Published: Jan. 18, 2024

Dementia is the most critical neurodegenerative disease that gradually destroys memory and other cognitive functions. Hence early detection utmost necessary to build an effective model, its required understand type, symptoms, stages & causes. This review work deep dives into dementia type which still incurable i.e., "Alzheimer's" surveyed different biomarkers (CFS, Aβ42, t-Tau, p-Tau, miRNAs, HNE, TNF, etc.) as well diagnosis methodologies - APM, AI/ML, Deep learning Fuzzy logic algorithms implementation based on medical images data generated using CTS, MRI, sMRI, fMRI, PET, Retinal photography (most cost effective) those were used in AD detection. summarizes various techniques mentioned survey/articles/research papers analyzed their accuracy, sources, affordability, features issues. Based this paper, new may be designed. study emphasis use of retinal affordable, accessible, efficient future system

Language: Английский

---

CCADD: An Online Webserver for Alzheimer's Disease Detection from Brain MRI

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 177, P. 108622 - 108622

Published: May 16, 2024

Language: Английский

---