Academic Journal
Introducing an ensemble method for the early detection of Alzheimer's disease through the analysis of PET scan images
| العنوان: | Introducing an ensemble method for the early detection of Alzheimer's disease through the analysis of PET scan images |
|---|---|
| المؤلفون: | Arezoo Borji, Taha-Hossein Hejazi, Abbas Seifi |
| المصدر: | International Journal of Research in Industrial Engineering, Vol 14, Iss 1, Pp 65-85 (2025) |
| بيانات النشر: | Ayandegan Institute of Higher Education,, 2025. |
| سنة النشر: | 2025 |
| المجموعة: | LCC:Industrial engineering. Management engineering |
| مصطلحات موضوعية: | alzheimer’s disease, convolutional neural networks, pet scan images, voxel-based morphometry, ensemble methods, Industrial engineering. Management engineering, T55.4-60.8 |
| الوصف: | Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that primarily affects cognitive functions such as memory, thinking, and behavior. In this disease, there is a critical phase, Mild Cognitive Impairment (MCI), that is important to be diagnosed early since some patients with progressive MCI will develop the disease. When a person is in MCI, they still have significant cognitive issues, especially with memory, but they are still able to perform many daily tasks on their own. This study delves into the challenging task of classifying Alzheimer's patients into four distinct groups: Control Normal (CN), progressive Mild Cognitive Impairment (pMCI), stable Mild Cognitive Impairment (sMCI), and AD. This classification is based on a thorough examination of Positron Emission Tomography (PET) scan images obtained from the ADNI dataset, which provides a comprehensive understanding of the disease's progression. Several deep-learning and traditional machine-learning models have been used to detect AD. In this paper, three deep-learning models, namely VGG16 and AlexNet, and a custom Convolutional Neural Network (CNN) with 8-fold cross-validation, have been used for classification. Finally, an ensemble technique is used to improve the overall result of these models. The classification results show that using deep-learning models to tell the difference between MCI patients gives an overall average accuracy of 93.13% and an Area Under the Curve (AUC) of 94.4%. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2783-1337 2717-2937 |
| Relation: | https://www.riejournal.com/article_207736_6b17ab48e20a8892b834e38033fb97cf.pdf; https://doaj.org/toc/2783-1337; https://doaj.org/toc/2717-2937 |
| DOI: | 10.22105/riej.2024.452413.1434 |
| URL الوصول: | https://doaj.org/article/4ca2ce00f50d40769acc7186093ccb2f |
| رقم الانضمام: | edsdoj.4ca2ce00f50d40769acc7186093ccb2f |
| قاعدة البيانات: | Directory of Open Access Journals |
| تدمد: | 27831337 27172937 |
|---|---|
| DOI: | 10.22105/riej.2024.452413.1434 |