Development and Optimization of Deep Learning Systems for MRI Analysis in Alzheimer’s Disease Monitoring

• Autorzy: Podolszańska Jolanta

Identyfikatory

DOI

10.26636/jtit.2024.4.1815

• Języki publikacji: EN

Abstrakty

EN

Alzheimer’s disease is one of the leading causes of dementia worldwide, and its increasing prevalence presents significant diagnostic and therapeutic challenges, particularly in an aging population. Current diagnostic methods, including patient history reviews, neuropsychological tests, and MRI scans, often fail to achieve adequate sensitivity and specificity levels. In response to these challenges, this study introduces an advanced convolutional neural network (CNN) model that combines ResNet-50 and Inception V3 architectures to classify, with a high degree of precision, the stages of Alzheimer’s disease based on MRI. The model was developed and evaluated using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and classifies MRI scans into four clinical categories representing different stages of disease severity. The evaluation results, based on the precision, sensitivity and F1 score metrics, demonstrate the effectiveness of the model. Additional augmentation techniques and differential class weighting further enhance the accuracy of the model. Visualization of results using the t-SNE method and the confusion matrix underscores the ability to distinguish between disease categories, supporting the model’s potential to aid in neurological diagnosis and classification.

Słowa kluczowe

EN

Alzheimer disease; convolutional neural network; Inception V3; ResNet-50; t-SNE analysis

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2024
• Tom: nr 4
• Strony: 56--61
• Opis fizyczny: Bibliogr. 19 poz., rys., wykr.

Twórcy

autor

Podolszańska Jolanta

• Jan Długosz University, Częstochowa, Poland

• https://orcid.org//0000-0002-6032-5654

Bibliografia

• [1] J.H. Shin, “Dementia Epidemiology Fact Sheet 2022”, Annals of Rehabilitation Medicine, vol. 46, no. 2, pp. 53–59, 2022 (https://doi.org/10.5535/arm.22027).
• [2] World Health Organization, Dementia, Geneva, Switzerland: World Health Organization, 2024 [Online] (https://www.who.int/news-room/fact-sheets/detail/dementia).
• [3] V.A. Ciurea et al., “Alzheimer’s Disease: 120 years of Research and Progress”, Journal of Medicine and Life, vol. 16, no. 2, pp. 173–177,2023 (https://doi.org/10.25122/jml-2022-0111).
• [4] J.A. Soria Lopez, H.M. Gonzalez, and G.C. Leger, “Alzheimer’s Disease”, in: Handbook of Clinical Neurology, pp. 231–255, 2019 (https://doi.org/10.1016/B978-0-12-804766-8.00013-3).
• [5] J.S. Snowden, “Changing Perspectives on Frontotemporal Dementia: A Review”, Journal of Neuropsychology, vol. 17, no. 2, pp. 211–234, 2023 (https://doi.org/10.1111/jnp.12297).
• [6] A. Alzheimer, “On Certain Peculiar Diseases of Old Age”, in: History of Psychiatry, H. Forstl and R. Levy, vol. 2, no. 5, pp. 71–101, 1991 (https://doi.org/10.1177/0957154X9100200505).
• [7] A.J. Intorcia et al., “A Modification of the Bielschowsky Silver Stain for Alzheimer Neuritic Plaques: Suppression of Artifactual Staining by Pretreatment with Oxidizing Agents”, BioRxiv, 2019 (https://doi.org/10.1101/570093).
• [8] N. Yaqoob et al., Prediction of Alzheimer’s Disease Stages Based on ResNet-Self-attention Architecture with Bayesian Optimization and Best Features Selection”, Frontiers in Computational Neuroscience, 2024 (https://doi.org/10.3389/fncom.2024.1393849).
• [9] H. Habehh and S. Gohel, “Machine Learning in Healthcare”, Current Genomics, vol. 22, no. 4, pp. 291–300, 2021 (https://doi.org/10.2174/1389202922666210705124359).
• [10] R.M. Hernandez et al., “Application of Machine Learning on MRI Scans for Alzheimer’s Disease Early Detection”, Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology, pp. 143–149, 2023 (https://doi.org/10.1145/3626641.3627609).
• [11] M.H. Alshayeji, “Alzheimer’s Disease Detection and Stage Identification from Magnetic Resonance Brain Images Using Vision Transformer”, Machine Learning: Science and Technology, vol. 5, no. 3, art. no. 035011, 2024 (https://doi.org/10.1088/2632-2153/ad5fdc).
• [12] M.G. Hussain and Y. Shiren, “Identifying Alzheimer Disease Dementia Levels Using Machine Learning Methods”, Medical Research Archives, vol. 11, no. 7.1, 2023 (https://doi.org/10.18103/mra.v11i7.1.4039).
• [13] V.K. Tiwari, P. Indic, and S. Tabassum, “Machine Learning Classification of Alzheimer’s Disease Stages Using Cerebrospinal Fluid Biomarkers Alone”, arXiv, 2024 (https://doi.org/10.48550/arXiv.2401.00981).
• [14] S.E. Sorour et al., “Classification of Alzheimer’s Disease Using MRI Data Based on Deep Learning Techniques”, Journal of King Saud University-Computer and Information Sciences, vol. 36, no. 2, art. no. 101940, 2024 (https://doi.org/10.1016/j.jksuci.2024.101940).
• [15] D.A. Arafa et al., “A Deep Learning Framework for Early Diagnosis of Alzheimer’s Disease on MRI Images”, Multimedia Tools and Applications, vol. 83, pp. 3767–3799, 2024 (https://doi.org/10.1007/s11042-023-15738-7).
• [16] A.M. El-Assy, H.M. Amer, H.M. Ibrahim, and M.A. Mohamed, “A Novel CN Architecture for Accurate Early Detection and Classification of Alzheimer’s Disease Using MRI Data”, Scientific Reports, vol. 14, art. no. 3463, 2024 (https://doi.org/10.1038/s41598-024-53733-6).
• [17] Y. Liu et al., “MPC-STANet: Alzheimer’s Disease Recognition Method Based on Multiple Phantom Convolution and Spatial Transformation Attention Mechanism”, Frontiers in Aging Neuroscience, vol. 14, art. no. 918462, 2022 (https://doi.org/10.3389/fnagi.2022.918462).
• [18] S. Ha, Y. Yoon, and J. Lee, “Meta-ensemble Learning with a Multiheaded Model for Few-shot Problems”, ICT Express, vol. 9, no. 5, pp. 909–914, 2023 (https://doi.org/10.1016/j.icte.2022.09.001).
• [19] https://www.kaggle.com/datasets