Performance Comparison Between Different Per-trained Models with Resnet-53 Using MRI and PET Scan Alzheimer’s Disease Image Dataset

Rama Lakshmi Boyapati; Radhika Yalavarthi

doi:10.52756/ijerr.2024.v46.007

Authors

Rama Lakshmi Boyapati Department of Computer Science and Engineering, GITAM School of Technology, GITAM (Deemed-to-be University), Visakhapatnam-530045, Andhra Pradesh, India https://orcid.org/0000-0001-7041-2260
Radhika Yalavarthi Department of Computer Science and Engineering, GITAM School of Technology, GITAM (Deemed-to-be University), Visakhapatnam-530045, Andhra Pradesh, India https://orcid.org/0000-0001-6898-2467

DOI:

https://doi.org/10.52756/ijerr.2024.v46.007

Keywords:

Bottleneck, Desnet121, Inception V3, Neuroimaging, RESNET 50, RESNET 101, VGG-16

Abstract

In order to provide immediate support and medical care to identify Alzheimer's disease (AD) as early as possible. By analysing patterns and features in large datasets, these approaches can identify subtle changes in brain structure, function, or biomarkers that may indicate the presence of the Disease at an early stage. Early detection allows for timely intervention and treatment, potentially improving patient outcomes. Using MRI and PET scans image datasets particular to Alzheimer's disease. This study compares the performance of several pre-trained models, like VGG-16, VGG-19, RESNET 50, INCEPTION V3 and Desnet121 with the proposed model ResNet-53. The main goal is to assess and compare how well these models are able to discriminate between healthy people and people with AD. By comparing each model's accuracy and precision, we use transfer learning to optimize them all. The performance of the RESNET-53 is strong to classify the AD and the accuracy is 99.65%. Our findings showed significant differences in performance, with certain models exhibiting higher accuracy in particular imaging modalities. In the proposed model the preprocessing will be initialized by a zero centering process then combined Gaussian filter with bilateral filter. For feature extraction, ResNet is used for its residual connections. In the ResNet architecture first layers are freezed and the last 3 layers are customized for feature extraction. The study emphasizes how integrating deep learning approaches with a variety of imaging modalities may enhance diagnosis accuracy. The accuracy obtained using VGG 16, VGG 19, ResNet 101, RESNET 50, DenseNet 121 and Inception V3 models are 89.61%, 92.81%, 96.32%, 95.27%, 97.80% and 96.44%. The proposed model provides a classification accuracy of 99.65%. The proposed model ResNet 53 has more accuracy. “ResNet-53 outperforms baseline models, achieving a precision of 98.96%, recall of 95%, and an F1-score of 96.97%, which demonstrates its ability to handle class imbalance more effectively than previous approaches.

References

Acharya, H., Mehta, R., & Kumar Singh, D. (2021). Alzheimer Disease Classification Using Transfer Learning. Proceedings-5th International Conference on Computing Methodologies and Communication (ICCMC) 2021, 1503–1508. https://doi.org/10.1109/ICCMC51019.2021.9418294

Aderghal, K., Afdel, K., Benois-Pineau, J., & Catheline, G. (2020). Improving Alzheimer’s stage categorization with Convolutional Neural Network using transfer learning and different magnetic resonance imaging modalities. Heliyon, 6(12). https://doi.org/10.1016/j.heliyon.2020.e05652

Aliaa, El-Gawady., Mohamed, A. Makhlouf., BenBella, S. Tawfik., & Hamed, N. (2022). Machine Learning Framework for the Prediction of Alzheimer’s Disease Using Gene Expression Data Based on Efficient Gene Selection. Symmetry, 2022, 491. https://doi.org/10.3390/sym14030491

Ambily, F., & Immanuel, A.P. (2021). Early detection of Alzheimer’s disease using an ensemble of pre-trained models. 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), 13(1). https://doi.org/10.1109/ICAIS50930.2021.9395988

Aparna, M., and Rao, B.S. (2023). A novel automated deep learning approach for Alzheimer’s disease classification. IAES International Journal of Artificial Intelligence, 12(1), 451. https://doi.org/0.11591/ijai.v12.i1 .pp451-458

Bringas, S., Salomón, S., Duque, R., Lage, C., & Montaña, J. L. (2020). Alzheimer’s Disease stage identification using deep learning models. Journal of BiomedicalInformatics,109. https://doi.org/10.1016/j.jbi.2020.103514

Dixit, A., Gupta, A., Chaplot, N., & Bharti, V. (2024). Emoji Support Predictive Mental Health Assessment Using Machine Learning: Unveiling Personalized Intervention Avenues. International Journal of Experimental Research and Review, 42, 228-240. https://doi.org/10.52756/ijerr.2024.v42.020

Ebrahimi, A., Luo, S., & Chiong, R. (2020). Introducing Transfer Learning to 3D ResNet-18 for Alzheimer’s Disease Detection on MRI Images. 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), 1–6. https://doi.org/10.1109/ivcnz51579.2020.9290616

Haloi, R., & Chanda, D., (2024). Performance Analysis of KNN, Naïve Bayes, and Extreme Learning Machine Techniques on EEG Signals for Detection of Parkinson’s Disease. International Journal of Experimental Research and Review, 43(Spl Vol), 32–41. https://doi.org/10.52756/ijerr.2024.v43spl.003

Hansen, B. (2020). Diffusion Kurtosis Imaging as a Tool in Neurotoxicology. Neurotox Research, 37(1), 41–47. https://doi.org/10.1007/s12640-019-00100-3

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770-778. https://doi.org/10.1109/CVPR.2016.90

Himabindu, D. D., Pranalini, B., Kumar, M. S., Neethika, A., Sree N, B., C, M., B, H., & S, K. (2024). Deep CNN-based Classification of Brain MRI Images for Alzheimer’s Disease Diagnosis. International Journal of Experimental Research and Review, 41(Spl Vol), 43–54. https://doi.org/10.52756/ijerr.2024.v41spl.004

Jain, P., & Thada, V. (2024). Securing the Data Using an Efficient Machine Learning Technique. International Journal of Experimental Research and Review, 40(SplVolume), 217-226. https://doi.org/10.52756/ijerr.2024.v40spl.018

Khan, R., Akbar, S., Mehmood, A., Shahid, F., Munir, K., Ilyas, N., Asif, M., & Zheng, Z. (2023). A transfer learning approach for multiclass classification of Alzheimer’s disease using MRI images. Frontiers in Neuroscience, 16. https://doi.org/10.3389/fnins.2022.1050777

Li, Y., Haber, A., Preuss, C., John, C., Uyar, A., Yang, H. S., Logsdon, B. A., Philip, V., Krishna Murthy Karutur, R., & Carter, G. W. (2021). Transfer learning-trained convolutional neural networks identify novelmri biomarkers of Alzheimer’s disease progression. Alzheimer’s and Dementia: Diagnosis, Assessment and Disease Monitoring, 13(1). https://doi.org/10.1002/dad2.12140

Liu, S., Masurkar, A. V., Rusinek, H., Chen, J., Zhang, B., Zhu, W., Fernandez-Granda, C., & Razavian, N. (2022). The generalizable deep learning model for early Alzheimer's disease detection from structural MRIs. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-20674-x

Liu, T., Xu, F., & Zhang, D. (2024). Alzheimer's disease classification using hybrid deep learning models with MRI and PET scan images: A comparative analysis. Scientific Reports, 14, 5732. https://doi.org/10.1038/s41598-024-34735-9

Mehmood, A., Yang, S., Feng, Z., Wang, M., Ahmad, A. S., Khan C, R., Maqsood, M., & Yaqub, M. (2021). A Transfer Learning Approach for Early Diagnosis of Alzheimer’s Disease on MRI Images. http://adni.loni.usc.edu/wp-content/

Muhammed Raees, P. C., & Thomas, V. (2021). Automated detection of Alzheimer’s Disease using Deep Learning in MRI. Journal of Physics: Conference Series, 1921(1). https://doi.org/10.1088/1742-6596/1921/1/012024

Pal, R., Pandey, M., Pal, S., & Yadav, D. (2023). Phishing Detection: A Hybrid Model with Feature Selection and Machine Learning Techniques. Int. J. Exp. Res. Rev., 36, 99-108. https://doi.org/10.52756/ijerr.2023.v36.009

Raju, M., Thirupalani, M., Vidhyabharathi, S., & Thilagavathi, S. (2021). Deep Learning Based Multilevel Classification of Alzheimer’s Disease using MRI Scans. IOP Conference Series: Materials Science and Engineering, 1084(1), 012017. https://doi.org/10.1088/1757-899x/1084/1/012017

Rama Lakshmi, Boyapati., & Radhika, Y. (2024). Multimodal Machine Learning for Early Alzheimer's Disease Detection: Leveraging Cognitive Features, and Resnet-Based Image Analysis with SVM Tuning. International Journal of Intelligent Systems and Applications in Engineering (IJISAE), 12(3), 56–70

Ramalakshmi, B., & Radhika, Y. (2024). RESNET-53 for Extraction of Alzheimer’s Features Using Enhanced Learning Models. International Journal of Computational and Experimental Science and Engineering (IJCESEN), 10(4), 879-889. https://doi.org/10.22399/ijcesen.519

R. L. B., & R. Y. (2024). Resnet-53 for Alzheimer's Disease Detection from MRI Images and Analysis with SVM Tuning with Hyper Optimization Technique. 2024 4th International Conference on Sustainable Expert Systems (ICSES), Kaski, Nepal, pp.1065-1072. https://doi.org/10.1109/ICSES63445.2024.10763183.

Rao, K. V., Devi, J. A., Anuradha, Y., G, K., Kumar, M. S., & Rao, M. S. (2024). Enhancing Liver Disease Detection and Management with Advanced Machine Learning Models. International Journal of Experimental Research and Review, 42, 100–110. https://doi.org/10.52756/ijerr.2024.v42.009

Roy, P., Ghosh, D., Sanyal, R., Madhu, N.R., Dey, A. (2024). The Controversy Surrounding Drugs Against Neurodegenerative Disorders: Benefit or Harm? In: Pathak, S., Banerjee, A. (eds) Neuroprotective Effects of Phytochemicals in Brain Ageing. Springer, Singapore. pp. 373-386. https://doi.org/10.1007/978-981-99-7269 2_17

Sarawgi, U., Zulfikar, W., Soliman, N., & Maes, P. (2020). Multimodal Inductive Transfer Learning for Detection of Alzheimer’s Dementia and its Severity. http://arxiv.org/abs/2009.00700

Sekhar, C., Devi, J., Kumar, M., Swathi, K., Ratnam, P., & Rao, M. (2024). Enhancing Sign Language Understanding through Machine Learning at the Sentence Level. International Journal of Experimental Research and Review, 41(Spl Vol), 11-18. https://doi.org/10.52756/ijerr.2024.v41spl.002

Singh, A., & Kumar, R. (2024). Brain MRI Image Analysis for Alzheimer’s Disease (AD) Prediction Using Deep Learning Approaches. SN Computer Science, 5, 160. https://doi.org/10.1007/s42979-023-02461-1

Yadav, A., & Sharma, N. (2021). A review of pretrained models for medical image classification: Applications to Alzheimer’s disease. Journal of Computational Biology, 28(5), 517-529. https://doi.org/10.1089/cmb.2020.0325

Yang, L., Wang, X., Guo, Q., Gladstein, S., Wooten, D., Li, T., Robinson, W. Z., Sun, Y., & Huang, X. (2021). Deep Learning Based Multimodal Progression Modeling for Alzheimer's Disease. Statistics in Biopharmaceutical Research, 13(3), 337–343. https://doi.org/10.1080/19466315.2021.1884129

Zhang, Z., Yang, S., Zhang, X., & Zhao, Y. (2020). A comparative study of deep learning models for Alzheimer’s disease classification using MRI and PET scans. Medical Image Analysis, 65, 101794. https://doi.org/10.1016/j.media.2020.101794