A Review on Machine Learning and Deep Learning Methods for Detection of Alzheimer’s Disease
محل انتشار: اولین کنگره بین المللی هوش مصنوعی در علوم پزشکی
سال انتشار: 1402
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 68
نسخه کامل این مقاله ارائه نشده است و در دسترس نمی باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
AIMS01_267
تاریخ نمایه سازی: 1 مرداد 1402
چکیده مقاله:
Alzheimer’s disease (AD) is the most common type of dementia in which the condition of thepatient gets worst with time. Therefore, early diagnosis of AD can increase patients’ survival rate.Machine learning (ML) and deep learning (DL) algorithms as two main artificial intelligence(AI) methods for image analysis, can be used to assess brain magnetic resonance (MR) images inorder to early detection of AD. This study aimed to present a review on application of machinelearning and deep learning algorithms for accurate detection of Alzheimer’s disease. PubMed,ScienceDirect, Web of Science and Google Scholar databases were explored using different combinationsof the keywords “Alzheimer’s disease”, “deep learning”, “machine learning”, “artificialintelligence”, “radiomics”, and “MRI”. Ten more recent and relevant papers, were included in thestudy. Geometric features extracted from brain MR images comprised the main radiomics used astraining features by the AI methods for AD detection. The most frequent DL models were convolutionalneural networks (CNN) models with the maximum classification accuracy and sensitivityup to ۹۹%. Support vector machine (SVM) was also the most popular machine learning techniquewith maximum accuracy and sensitivity of ۹۹%. In conclusion, AI and radiomic features can offera powerful tool for the quantitative assessment and early diagnosis of AD.
کلیدواژه ها:
«Alzheimer’s Disease ، » Machine Learning» ، «Deep Learning» ، «Artificial Intelligence » ، «Brain Magnetic Resonance Images (MRI)».
نویسندگان
Laleh Rahmanian
Department of Radiologic Technology, School of Allied Medical Sciences, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
Marziyeh Tahmasbi
Department of Radiologic Technology, School of Allied Medical Sciences, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran