Scholarlink

Dementia is a cognitive disorder that affects the brain, with Alzheimer's Disease (AD) being its primary stage. AD leads to memory loss ( Maysam Orouskhani, Chengcheng Zhu et al.(2022),” Alzheimer’s disease detection from structural MRI using conditional deep triplet network”-Elsevier-Neuroscience Informatics 2(2022)100,066-Volume2,Issue4, 2022,100,066 10.1016/j.neuri.2022.100066), difficulties in thinking, concentrating, and decision-making. This condition is among the leading causes of death in developed nations ( Alejandro Puente-Castro et al.(2020),” Automatic assessment of Alzheimer’s disease diagnosis based on deep learning techniques”- Elsevier-Computers in BiologyandMedicine-Volume120, 2020,103,764. 10.1016/j.compbiomed.2020.103764). Despite research showing promising results with computer-aided algorithms, there is currently no practical diagnostic method available for clinical use ( Islam, Jyoti, and Yanqing Zhang. “Brain MRI analysis for Alzheimer’s disease diagnosis using an ensemble system of deep convolutional neural networks.“ Springer Open-Brain; informatics 5 (2018). 10.1007/s42979-021–00,815-1;). Convolutional neural networks (CNNs), in particular, have been more and more prominent in deep learning models for AD detection studies in recent years. This is especially true when analyzing images from medical imaging modalities such as magnetic resonance imaging (MRI) and positron emission tomography (PET) ( informatics 5 (2018). 10.1007/s42979-021–00,815-1;Park et al. in Expert Syst Appl 140, 2020;). Although CNNs have demonstrated notable improvements in picture identification for AD diagnosis, the lack of sufficient imaging datasets makes it difficult to apply these models in practice. This research examines the state of deep learning-based AD detection at the moment. The most recent research and trends in this field are highlighted via a thorough assessment of the literature that includes more than 100 publications. This review centers on critical biomarkers, required pre-processing procedures, and different methods for neuroimaging data analysis from both single- and multimodality studies.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Using Deep Learning Techniques for Predictive Analysis of Alzheimer's Disease Early Diagnosis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Arif Ali,
  • Ritika Mehra

摘要

Dementia is a cognitive disorder that affects the brain, with Alzheimer's Disease (AD) being its primary stage. AD leads to memory loss ( Maysam Orouskhani, Chengcheng Zhu et al.(2022),” Alzheimer’s disease detection from structural MRI using conditional deep triplet network”-Elsevier-Neuroscience Informatics 2(2022)100,066-Volume2,Issue4, 2022,100,066 10.1016/j.neuri.2022.100066), difficulties in thinking, concentrating, and decision-making. This condition is among the leading causes of death in developed nations ( Alejandro Puente-Castro et al.(2020),” Automatic assessment of Alzheimer’s disease diagnosis based on deep learning techniques”- Elsevier-Computers in BiologyandMedicine-Volume120, 2020,103,764. 10.1016/j.compbiomed.2020.103764). Despite research showing promising results with computer-aided algorithms, there is currently no practical diagnostic method available for clinical use ( Islam, Jyoti, and Yanqing Zhang. “Brain MRI analysis for Alzheimer’s disease diagnosis using an ensemble system of deep convolutional neural networks.“ Springer Open-Brain; informatics 5 (2018). 10.1007/s42979-021–00,815-1;). Convolutional neural networks (CNNs), in particular, have been more and more prominent in deep learning models for AD detection studies in recent years. This is especially true when analyzing images from medical imaging modalities such as magnetic resonance imaging (MRI) and positron emission tomography (PET) ( informatics 5 (2018). 10.1007/s42979-021–00,815-1;Park et al. in Expert Syst Appl 140, 2020;). Although CNNs have demonstrated notable improvements in picture identification for AD diagnosis, the lack of sufficient imaging datasets makes it difficult to apply these models in practice. This research examines the state of deep learning-based AD detection at the moment. The most recent research and trends in this field are highlighted via a thorough assessment of the literature that includes more than 100 publications. This review centers on critical biomarkers, required pre-processing procedures, and different methods for neuroimaging data analysis from both single- and multimodality studies.