EARLY DIAGNOSIS OF ALZHEIMER’S DISEASE USING DEEP LEARNING AND IMAGE PROCESSING ON BRAIN MRI IMAGES

Harish Barapatre; Nilesh Pawar; Shweta Mohite

doi:10.29121/shodhkosh.v5.i7.2024.6000

Authors

Dr. Harish Barapatre Yadavrao Tasgaonkar Institute, Dept of Computer, Karjat, India
Dr. Nilesh Pawar Yadavrao Tasgaonkar Institute, Dept. Of Computer, Karjat, India
Shweta Mohite Yadavrao Tasgaonkar Institute, Dept. Of Computer, Karjat, India

DOI:

https://doi.org/10.29121/shodhkosh.v5.i7.2024.6000

Keywords:

Brain Segmentation, Skull Stripping, Threshold, Seed Region Growing, Alzheimer’s Disease, Convolutional Neural Network, Deep Learning

Abstract [English]

To take preventative action, Alzheimer’s disease (AD) must be identified early. Particularly in those over 60, Alzheimer’s disease is regarded as one of the acute illnesses that kill people. Because of the diversity and complexity of brain tissue, using MRI (Magnetic Resonance Imaging) to classify Alzheimer’s disease is thought to be a challenging process. As a result, the systems for Alzheimer’s disease detection and classifi- cation comprise four stages: MRI pre-processing, segmentation, feature extraction, and classification. The primary goal of the first stage is to remove any noise from medical resonance images (MRIs) that could be caused by light reactions or errors in the imaging medium. The second step involves extracting the region of interest, which is the Alzheimer’s disease zone. To prepare for the classification process, the third stage will involve obtaining and storing MRI image features in an image vector. The fourth stage will then involve the classifier, which will specify the Alzheimer-type picture segmentation, thereby recognizing the disease at an early stage. The hybrid methodology employed in this study blends deep learning-based convolutional neural networks (CNNs) with traditional classifiers such as support vector machines (SVM) and random forests. The interpretabil- ity of traditional classification methods is combined with the advantages of deep learning’s feature extraction capabilities in this framework achieved higher accuracy when compared to the current CNN methods.

References

Su, Y., Sanchez, J. M., Brun˜a, R., Farzin, D., Wong-Lin, K., & Prasad, G. (2021). Integrated space–frequency–time domain feature extraction for MEG-based Alzheimer’s disease classification. Brain Informatics, 8(24), 1–11. https://doi.org/10.1186/s40708-021-00145-1 DOI: https://doi.org/10.1186/s40708-021-00145-1

M. B. T., Zenia, N. Z., Kaiser, M. S., & Mamun, S. A. (2020). Application of deep learning in detecting neurological disorders from magnetic resonance images: A survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia. Brain Informatics, 7(11), 1–21. https://doi.org/10.1186/s40708-020-00112-2

Pang, L., Zhou, X., Sun, Y., & Li, J. (2022). Focused on sleep disorders and behavioral sub syndrome analysis in Alzheimer’s disease patients. Public Health and Preventive Medicine, 33, 154–157.

Lombardi, A., Diacono, D., Amoroso, N., Biecek, P., Monaco, A., Bellantuono, L., et al. (2022). A robust framework to investigate the reliability and stability of explainable artificial intelligence markers of Mild Cognitive Impairment and Alzheimer’s Disease. Brain Informatics, 9(17), 1–17. https://doi.org/10.1186/s40708-022-00165-5 DOI: https://doi.org/10.21203/rs.3.rs-1550479/v1

Naik, B., Mehta, A., & Shah, M. (2020). Denouements of ma- chine learning and multimodal diagnostic classification of Alzheimer’s disease. Visual Computing for Industry, Biomedicine, and Art. https://doi.org/10.1186/s42492-020-00062-w DOI: https://doi.org/10.1186/s42492-020-00062-w

Zheng, W., Yao, Z., Li, Y., Zhang, Y., Hu, B., Wu, D., & Alzheimer’s disease Neuroimaging Initiative. (2019). Brain connectivity based pre- diction of Alzheimer’s disease in patients with mild cognitive impair- ment based on multi-modal images. Frontiers in Human Neuroscience, 13, 399. https://doi.org/10.3389/fnhum.2019.00399 [ DOI: https://doi.org/10.3389/fnhum.2019.00399

Ram´ırez, J., Go´rriz, J. M., Ortiz, A., Mart´ınez-Murcia, F. J., Segovia, F., Salas-Gonzalez, D & Alzheimer’s Disease Neuroimaging Initiative. (2018). Ensemble of random forests one vs. rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares. Journal of Neuroscience Methods, 302, 47–57. https://doi.org/10.1016/j.jneumeth.2017.12.005 DOI: https://doi.org/10.1016/j.jneumeth.2017.12.005

Altaf, T., Anwar, S. M., Gul, N., Majeed, M. N. & Majid, M. (2018). Multi-class Alzheimer’s disease classification using image and clini- cal features. Biomedical Signal Processing and Control, 43, 64–74. https://doi.org/10.1016/j.bspc.2018.02.019 DOI: https://doi.org/10.1016/j.bspc.2018.02.019

Sharma, R., Goel, T., Tanveer, M., & Murugan, R. (2022). FDN-ADNet: Fuzzy LS-TWSVM based deep learning network for prognosis of the Alzheimer’s disease using the sagittal plane of MRI scans. Applied Soft Computing, 115, 108099. https://doi.org/10.1016/j.asoc.2021.108099 DOI: https://doi.org/10.1016/j.asoc.2021.108099

Zhang, J., He, X. H., Qing, L. B., Gao, F., & Wang, B. (2022). BPGAN: Brain PET synthesis from MRI using generative ad- versarial network for multi-modal Alzheimer’s disease diagnosis. Computer Methods and Programs in Biomedicine, 217, 106676. https://doi.org/10.1016/j.cmpb.2022.106676 DOI: https://doi.org/10.1016/j.cmpb.2022.106676

Hazarika, R. A., Kandar, D., & Maji, A. K. (2022). An experimental analysis of different deep learning based models for Alzheimer’s disease classification using brain magnetic resonance images. Journal of King Saud University - Computer and Information Sciences, 34, 8576–8598. https://doi.org/10.1016/j.jksuci.2021.09.003 [ DOI: https://doi.org/10.1016/j.jksuci.2021.09.003

Neelum, N., Sellappan, P., Abdul, Q., Ahmad, I., & Alassafi, M.O. (2021). Brain tumor classification based on fine-tuned models and the ensemble method. Computational Materials and Continua, 67, 3967–3982. DOI: https://doi.org/10.32604/cmc.2021.014158

Islam, J.,& Zhang, Y. (2018). Brain MRI analysis for Alzheimer’s disease diagnosis using an ensemble system of deep convolutional neural networks. Brain Informatics, 5(2), 1–14. https://doi.org/10.1186/s40708-018-0080-3

M. B. T., Zenia, N. Z., Kaiser, M. S., & Mamun, S. A. (2020). Application of deep learning in detecting neurological disorders from magnetic resonance images: A survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia. Brain Informatics, 7(11), 1–21. https://doi.org/10.1186/s40708-020-00112-2 DOI: https://doi.org/10.1186/s40708-020-00112-2

Alzheimer’s Association. (2021). 2021 Alzheimer’s disease facts and figures. Alzheimer’s & Dementia, 17, 327–406. https://doi.org/10.1002/alz.12328 DOI: https://doi.org/10.1002/alz.12328

Islam, J., & Zhang, Y. (2018). Brain MRI analysis for Alzheimer’s disease diagnosis using an ensemble system of deep convolutional neural networks. Brain Informatics, 5(2), 1–14. https://doi.org/10.1186/s40708-018-0080-3 DOI: https://doi.org/10.1186/s40708-018-0080-3

Liang, G. W., Zhang, K., Cao, P., Liu, X., Yang, J., & Za- iane, O. (2021). Rethinking modeling Alzheimer’s disease progres- sion from a multi-task learning perspective with deep recurrent neu- ral network. Computers in Biology and Medicine, 138, 104935. https://doi.org/10.1016/j.compbiomed.2021.104935 DOI: https://doi.org/10.1016/j.compbiomed.2021.104935

Najmul, H., Abu, S. M. M., & Jungpil, S. (2024). Residual- based multi-stage deep learning framework for computer-aided Alzheimer’s disease detection. Journal of Imaging, 10(6), 141. https://doi.org/10.3390/jimaging10060141 DOI: https://doi.org/10.3390/jimaging10060141

Oh, K., Chung, Y.-C., Kim, K. W., Kim, W.-S., & Oh, I.-S. (2020).Classification and visualization of Alzheimer’s disease using volumetric convolutional neural network and transfer learning. Scientific Reports, 10(1), 1–16. https://doi.org/10.1038/s41598-020-62490-1 DOI: https://doi.org/10.1038/s41598-020-62490-1