Early detection of Alzheimer's Disease and Dementia Using Deep Convolutional Neural Networks DOI

G. Lakshmi Praveena,

G. P. Ramesh

Published: April 26, 2024

Alzheimer's disease (AD) is a progressive of the nervous system brain that weakens functions which leads patient to bedridden. Overall dementia cases are approximately 75% elderly people above 65 years age worldwide. Early detection AD constitute nearly 2-5%. Detecting earlier difficult and challenging task, requires human experts MRI reports. An alternative approach for early such as convolution neural network has been proposed in this paper with more reliable cost-efficient. From 3D image report, Disease Dementia detected also stages diagnosed using CNN. The CNNs datasheet on sMRI loaded online database. Classification task analysed evaluated ADNet. This analysis utilizes Magnetic Resonance (MR) images Convolutional Neural Network (CNN) architecture deep learning pipeline. classify based stage into Mild (MD), Very (VMD)., Non-dementia (ND), Moderate (MoD). results outperformed high accuracy 99.94 %.

Language: Английский

Conversion-aware forecasting of Alzheimer’s disease via featurewise attention DOI Creative Commons

Elvan Karasu,

İnci M. Baytaş

Pattern Analysis and Applications, Journal Year: 2025, Volume and Issue: 28(2)

Published: March 20, 2025

Language: Английский

Citations

1
Identifying the mediating role of brain atrophy on the relationship between DNA damage repair pathway and Alzheimer's disease: A Mendelian randomization analysis and mediation analysis DOI

Wei Bao,

Haidi Bi,

Lishuo Chao

et al.

Journal of Alzheimer s Disease, Journal Year: 2025, Volume and Issue: unknown

Published: May 2, 2025

Background DNA damage and repair (DDR) structural atrophies in different brain regions were recognized as critical factors the onset of Alzheimer's disease (AD). Objective We utilized Mendelian randomization (MR) to examine causal effects DDR-related molecular traits on AD potential mediating roles region volumes. Methods In primary analysis, we public genome-wide association studies summary data from existing datasets, including gene expression, methylation, protein levels quantitative trait loci (eQTL, mQTL, pQTL) both blood their associations by summary-data-based MR analysis additional five two-sample methods. Subsequently, mediation explored mediate 13 imaging-derived volume phenotypes between DDR pathways through a network design. Results found that volumes right thalamus proper global cerebral white matter mediated EGFR relatively weak lateral ventricle involving CHRNE, DNTT, AD. Conclusions identified relationships among pathways, specific volumes, Monitoring these genes developing targeted drugs may help detect interrupt early progression

Language: Английский

Citations

0
Comparative Analysis of Convolutional Neural Network and Support Vector Machine for the Prediction of Alzheimer's Disease DOI

Nimish Selot,

Aayush Panwa,

Anju Shukla

et al.

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 56 - 66

Published: Jan. 1, 2025

Language: Английский

Citations

0
Multi-knowledge informed deep learning model for multi-point prediction of Alzheimer’s disease progression DOI

Kai Wu,

Hong Wang,

Feiyan Feng

et al.

Neural Networks, Journal Year: 2025, Volume and Issue: 185, P. 107203 - 107203

Published: Feb. 1, 2025

Language: Английский

Citations

0
Early detection of Alzheimer's Disease and Dementia Using Deep Convolutional Neural Networks DOI

G. Lakshmi Praveena,

G. P. Ramesh

Published: April 26, 2024

Alzheimer's disease (AD) is a progressive of the nervous system brain that weakens functions which leads patient to bedridden. Overall dementia cases are approximately 75% elderly people above 65 years age worldwide. Early detection AD constitute nearly 2-5%. Detecting earlier difficult and challenging task, requires human experts MRI reports. An alternative approach for early such as convolution neural network has been proposed in this paper with more reliable cost-efficient. From 3D image report, Disease Dementia detected also stages diagnosed using CNN. The CNNs datasheet on sMRI loaded online database. Classification task analysed evaluated ADNet. This analysis utilizes Magnetic Resonance (MR) images Convolutional Neural Network (CNN) architecture deep learning pipeline. classify based stage into Mild (MD), Very (VMD)., Non-dementia (ND), Moderate (MoD). results outperformed high accuracy 99.94 %.

Language: Английский

Citations

1