Vol. 5 No. 2 (2023), Articles
Vol. 5 No. 2 (2023)

Real-Time Images and Deep Learning to Identify Alzheimer's Disease in a Web Application

Articles
Published 19-06-2023
V. Surendar
Department of Information Technology, Hindustan Institute of Technology and Science, Chennai. Tamil Nadu, India
E. Sriram
Department of Information Technology, Hindustan Institute of Technology and Science, Chennai. Tamil Nadu, India
K. Karunakaran
Department of Information Technology, Hindustan Institute of Technology and Science, Chennai. Tamil Nadu, India
S. Sudharshan
Department of Information Technology, Hindustan Institute of Technology and Science, Chennai. Tamil Nadu, India
M. Yuvaraja
Department of Information Technology, Hindustan Institute of Technology and Science, Chennai. Tamil Nadu, India
PDF

Keywords

Deep learning
convolutional neural network
image classification
data imbalance
over-sampling
SMOTE
TensorFlow

How to Cite

Real-Time Images and Deep Learning to Identify Alzheimer’s Disease in a Web Application. (2023). Journal of Information Technology and Digital World, 5(2), 144-158. https://doi.org/10.36548/jitdw.2023.2.005
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Abstract

Alzheimer's is a neurological condition that affects millions of individuals throughout the world. Early detection is critical for optimal treatment and management of this condition. This research presents a classification model that uses Convolutional Neural Networks (CNNs) to reliably identify the Alzheimer's disease using brain MRI scans. A publicly available dataset of brain MRI images divided into four categories: mild dementia, moderate dementia, non-dementia, and very mild dementia, has been utilized. When compared to the other classes, the number of samples for 'ModerateDemented' was found to be significantly lower, showing class imbalance. To solve this, the study oversamples the data by Synthetic Minority Over-sampling Technique (SMOTE) and generates extra samples. The proposed method augments the data utilizing the TensorFlow ImageDataGenerator. The study uses a CNN model with several sorts of normalization blocks. The suggested model achieved an accuracy of 95.2%, for the test set outperforming prior state-of-the-art techniques.

PDF

References

kaggle.com/datasets/sachinkumar413/alzheimer-mri-dataset

Brain Tumor Detection and Classification Using Neural Network Classifier" by N. H. M. Anas, N. N. M. Shariff, and H. Arof, published in 2019 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

Automated brain tumor detection and segmentation using U-Net based fully convolutional networks" by S. Mohan, R. Thirumal, and S. Vasudevan, published in 2019 IEEE International Conference on Advanced Computational and Communication Paradigms (ICACCP).

"A Deep Learning Approach for Brain Tumor Detection and Classification Using MRI Images" by V. Ravikumar, P. Deepak, K. Rajasekhar, and K. B. Madhuri, published in 2020 IEEE International Conference on Computational Intelligence in Data Science (ICCIDS).

"Automatic Detection and Segmentation of Brain Tumor Using Machine Learning Techniques" by A. S. A. Ibrahim, H. A. Ali, M. M. Kashef, and H. M. Abdelkader, published in 2020 IEEE 7th International Conference on Engineering Technologies and Applied Sciences (ICETAS).

"Brain Tumor Detection and Classification using Convolutional Neural Network and Transfer Learning" by S. S. H. S. Abirami, S. Dhivyaa, and V. Kiruthika, published in 2021 IEEE 7th International Conference on Advanced Computing and Communication Systems (ICACCS).

"Deep Convolutional Neural Network-Based Segmentation of Brain Tumors Using MRI Images" by M. A. Ahmadi, M. A. Hussain, M. A. M. Ali, and R. A. Rashid, published in IEEE Access in 2019.

"Multi-Modal Brain Tumor Segmentation Using Convolutional Neural Networks" by S. Kamnitsas, E. Ferrante, S. Parisot, C. Ledig, A. V. Nori, A. Criminisi, D. Rueckert, and B. Glocker, published in IEEE Transactions on Medical Imaging in 2017.

"Multi-Level Glioma Segmentation Using Fully Convolutional Neural Network" by S. Wang, J. Liu, C. Chen, Y. Qian, and H. Cheng, published in IEEE Access in 2018.

"Multimodal Brain Tumor Segmentation Using Spatially Convolved Neural Networks" by S. Baid, A. R. Jamkhedkar, and R. A. Borde, published in IEEE Access in 2021.

"Deep Learning-Based Brain Tumor Segmentation Using Transfer Learning" by Y. Wang, Z. Zhang, L. Li, Y. Xu, and Z. Tang, published in IEEE Access in 2019.

"Brain Tumor Segmentation Based on Deep Learning Algorithm" by Z. Jiang, S. Zhang, Y. Huang, L. Zhang, and X. Liu, published in IEEE Access in 2020.

"A Novel Deep Learning Approach for Brain Tumor Segmentation in MRI Images" by S. M. Zahraee, S. A. Hosseini, S. Karimi, and R. Samavi, published in IEEE Transactions on Medical Imaging in 2019.

"3D U-Net Convolutional Neural Network-Based Approach for Brain Tumor Segmentation Using MRI Images" by H. E. Hamed, A. H. Khalifa, and A. M. Rizk, published in IEEE Access in 2021.

"An Efficient Deep Learning Approach for Brain Tumor Segmentation on MRI Images" by R. Al-Sharif, W. Bouchkaraoui, and S. Ramakrishnan, published in IEEE Access in 2021.

"Improved Brain Tumor Segmentation Using a 3D Deep CNN and Spatial Pyramid Pooling" by Y. Xie, Y. Li, X. Mao published in IEEE Access in 2021.