Abstract
Objective:
The objective of this study is to develop a more effective early detection system for Alzheimer's disease (AD) using a Deep Residual Network
(ResNet) model by addressing the issue of convolutional layers in conventional Convolutional Neural Networks (CNN) and applying image
preprocessing techniques.
Methods:
The proposed method involves using Contrast Limited Adaptive Histogram Equalizer (CLAHE) and Boosted Anisotropic Diffusion Filters
(BADF) for equalization and noise removal and K-means clustering for segmentation. A ResNet-50 model with shortcut links between three
residual layers is proposed to extract features more efficiently. ResNet-50 is preferred over other ResNet types due to its intermediate depth,
striking a balance between computational efficiency and improved performance, making it a widely adopted and effective architecture for various
computer vision tasks. While other ResNet variations may offer higher depths, they are more prone to overfitting and computational complexity,
which can hinder their practical application. The proposed method is evaluated on a dataset of MRI scans of AD patients.
Results:
The proposed method achieved high accuracy and minimum losses of 95% and 0.12, respectively. While some models showed better accuracy,
they were prone to overfitting. In contrast, the suggested framework, based on the ResNet-50 model, demonstrated superior performance in terms
of various performance metrics, providing a robust and reliable approach to Alzheimer's disease categorization.
Conclusion:
The proposed ResNet-50 model with shortcut links between three residual layers, combined with image preprocessing techniques, provides an
effective early detection system for AD. The study demonstrates the potential of deep learning and image processing techniques in developing
accurate and efficient diagnostic tools for AD. The proposed method improves the existing approaches to AD classification and provides a
promising framework for future research in this area.
Keywords:
Alzheimer's disease, ResNet, CLAHE, Boosted anisotropic diffusion filter, K-means clustering, Convolutional Neural Networks (CNN).
[6]
Delmastro F, Di Martino F, Dolciotti C. Cognitive training, and stress detection in MCI frail older people through wearable sensors and machine learning. IEEE Access 2020; 8: 65573-90.
[23]
Ren F, Yang C, Qiu Q, et al. Exploiting discriminative regions of brain slices based on 2D CNNs for Alzheimer’s Disease classification IEEE Access 2019; 7: 181423-33.
[24]
Sumanth S, Suresh A. Survey on the identification of Alzheimer’s disease using magnetic resonance imaging (MRI) images. Int. J. Innov. Technol. Explore Eng 2019; 8: 3564-70.
[27]
Al-Shoukry S, Rassem TH, Makbol NM. Alzheimer’s Diseases detection by using deep learning algorithms. A Mini-Review; IEEE Access 2020; 8: 77131-41.
[29]
Ding Y, Jae Ho S, Michael GK, et al. A deep learning model to predict a diagnosis of Alzheimer's disease by using 18F-FDG PET of the brain. Radiology 2019; 2: 456-64.
[30]
Ebrahim D, Amr MT AE, Hossam EM, Hesham A. Alzheimer disease early detection using convolutional neural networks. In 2020 15th International Conference on Computer Engineering and Systems (ICCES) 2020; 1-6.
[31]
Suh C H, Shim W H, Kim S J, et al. Development and validation of a deep learning-based automatic brain segmentation and classification algorithm for Alzheimer's disease using 3D T1-weighted volumetric image. Am J Neuroradiol 2020; 12: 2227-34.
[32]
Salehi AW, Preety B, Brij BS, Gaurav G, Ankita U. A CNN model: Earlier diagnosis and classification of Alzheimer's disease using MRI. In 2020 International Conference on Smart Electronics and Communication (ICOSEC) 2020; 156-61.
[33]
Kundaram SS, Ketki CP. Deep learning-based Alzheimer disease detection; In proceedings of the fourth international conference on microelectronics, computing and communication systems. 2021; 587-97.
[34]
Al-Khuzaie , Fanar EK, Oguz B, Adil DD. Diagnosis of Alzheimer's disease using 2D MRI slices by a convolutional neural network. Applied Bionics and Biomechanics 2021; 2021
[35]
Nawaz H, Muazzam M, Sitara A, Farhan A, Irfan M, Seungmin Rho. A deep feature-based real-time system for Alzheimer's disease stage detection; Multimedia Tools and Applications. 2021; 28: 35789-807.
[36]
Carvalho ED, Carvalho ED, de Carvalho Filho AO, de Sousa AD, de Andrade Lira Rabulo R. COVID-19 diagnosis in CT images using CNN to extract features and multiple classifiers. IEEE Xplore. 26-28 October 2020, Cincinnati, OH, USA, pp. 425–431.
[38]
Sonker D. Comparison of histogram equalization techniques for image enhancement of grayscale images in natural and unnatural light. Int j eng res 2013; 8(9): 57-61.
[42]
Shehroz S, Khan AA. Cluster centre initialization algorithm for k-means cluster. Pattern Recognit Lett 2004; 1293-302.
[43]
Sorin S. An overview on clustering methods OSR J Eng 2004; 2(4): 719-25.
[44]
Abdul AS, Mohd YM, Zeehaida M, Abdul Aimi Salihai. Colour image segmentation approach for detection of malaria parasites using various colour models and k-means clustering. In WSEAS Transaction on Biology and Biomedicine 2013; 10(1): 41-55.
[50]
Islam J, Yanqing Z. Alzheimer’s disease neuroimaging initiative. Deep convolutional neural networks for automated diagnosis of Alzheimer’s disease and mild cognitive impairment using 3D brain MRI. In International Conference on Brain Informatics 2018; 359-69.
[52]
Özbay F A, Özbay E. Brain tumor detection with mRMR-based multimodal fusion of deep learning from MR images using Grad-CAM. Iran J Comput Sci 2023; 1-15.
[54]
Asif S, Yildirim M, Cinar A. An enhanced deep learning method for multi-class brain tumor classification using deep transfer learning. Multimed Tools Appl 2023; 1-28.
[56]
Wongvorachan T, Surina H, Okan B. Comparison of undersampling, oversampling, and SMOTE methods for dealing with imbalanced classification in educational data mining. 2023; 14(1): 54.