Enhancing early detection of Alzheimer's disease through hybrid models based on feature fusion of multi-CNN and handcrafted features

被引：1

作者：

Alayba, Abdulaziz M. ^{[1
]}

Senan, Ebrahim Mohammed ^{[2
,3
]}

Alshudukhi, Jalawi Sulaiman ^{[1
]}

机构：

[1] Univ Hail, Coll Comp Sci & Engn, Dept Informat & Comp Sci, Hail 81481, Saudi Arabia

[2] Hajjah Univ, Coll Appl Sci, Dept Comp Sci, Hajjah, Yemen

[3] Al Razi Univ, Fac Comp Sci & Informat Technol, Dept Artificial Intelligence, Sanaa, Yemen

来源：

SCIENTIFIC REPORTS | 2024年 / 14卷 / 01期

关键词：

CNN; XGBoost; ANN; Fusion features; RFE; AD; ACA; DIAGNOSIS;

D O I：

10.1038/s41598-024-82544-y

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

Alzheimer's disease (AD) is a brain disorder that causes memory loss and behavioral and thinking problems. The symptoms of Alzheimer's are similar throughout its development stages, which makes it difficult to diagnose manually. Therefore, artificial intelligence (AI) techniques address the limitations of manual diagnosis. In this study, the images were enhanced and the active contour algorithm (ACA) was used to extract regions of interest (ROI) such as soft tissue and white matter. Strategies have been developed to diagnose AD and differentiate its stages. The first strategy is using XGBoost and ANN networks with the features of MobileNet, DenseNet, and GoogLeNet models. The second strategy is by XGBoost and ANN networks with combined features of MobileNet-DenseNet121, DenseNet121-GoogLeNet and MobileNet-GoogLeNet. The third strategy combines XGBoost and ANN networks with combined features of MobileNet-DenseNet121-Handcrafted, DenseNet121-GoogLeNet-Handcrafted, and MobileNet-GoogLeNet-Handcrafted leading to improved accuracy of the strategies and improved efficiency. XGBoost with hybrid features of DenseNet-GoogLeNet-Handcrafted achieved an AUC of 98.82%, accuracy of 98.8%, sensitivity of 98.9%, accuracy of 97.08%, and specificity of 99.5%.

引用

页数：29

共 64 条

[1] Chen Z.R., Huang J.B., Yang S.L., Hong F.F., Role of cholinergic signaling in Alzheimer’s disease, Molecules, 27, (2022)
[2] Dementia due to Alzheimer’s disease (AD, ). Alzheimer’s Disease., pp. 21-30
[3] Review on Alzheimer’s disease: Past, present and future, J. Innovations Appl. Pharm. Sci. (JIAPS)., pp. 28-31
[4] Gupta V.B., Et al., Retinal changes in Alzheimer’s disease— integrated prospects of imaging, functional and molecular advances, Prog Retin Eye Res, 82, (2021)
[5] Gentile G., Mckinney K., Reboldi G., Intensive blood pressure control and cognitive impairment in chronic kidney disease: The jury is still out, Eur. J. Intern. Med, 101, pp. 32-33, (2022)
[6] Velandia P.P., Et al., Global and regional spending on dementia care from 2000–2019 and expected future health spending scenarios from 2020–2050: An economic modelling exercise, EClinicalMedicine, 45, (2022)
[7] Duara R., Barker W., Heterogeneity in Alzheimer’s disease diagnosis and progression rates: Implications for therapeutic trials, Neurotherapeutics, 19, pp. 8-25, (2022)
[8] Sannemann L., Et al., General practitioners’ attitude toward early and pre-dementia diagnosis of AD in five European countries—A MOPEAD project survey, Alzheimer’s Dementia: Diagnosis Assess. Disease Monit, 13, (2021)
[9] Littau J.L., Et al., Evidence of beta amyloid independent small vessel disease in familial Alzheimer’s disease, Brain Pathol, 32, (2022)
[10] Yaqoob N., Et al., Prediction of Alzheimer’s disease stages based on ResNet-Self-attention architecture with bayesian optimization and best features selection, Front. Comput. Neurosci, 18, (2024)

← 1 2 3 4 5 6 7 →