AUTHOR=Yaqoob Nabeela , Khan Muhammad Attique , Masood Saleha , Albarakati Hussain Mobarak , Hamza Ameer , Alhayan Fatimah , Jamel Leila , Masood Anum 

TITLE=Prediction of Alzheimer's disease stages based on ResNet-Self-attention architecture with Bayesian optimization and best features selection

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2024.1393849

DOI=10.3389/fncom.2024.1393849

ISSN=1662-5188

ABSTRACT=Alzheimer's disease (AD) is a neurodegenerative illness that impairs cognition, function, and behaviour by causing irreversible damage to multiple brain areas, including the hippocampus. A patient's and their family members' suffering will be lessened with an early diagnosis of AD. The automatic diagnosis technique is widely required due to the shortage of medical experts and eases the burden of medical staff. The automatic artificial intelligence (AI) based computerized method can help experts achieve better diagnosis accuracy and precision rates. This paper proposes a new automated framework for AD stage prediction based on the ResNet-Self architecture and Fuzzy entropy-controlled path-finding algorithm (FEcPFA). A data augmentation technique has been utilized to resolve the dataset imbalance issue. In the next step, we proposed a new deeplearning model based on the self-attention module. A resnet50 architecture is modified and connected with a self-attention block for important information extraction. The hyperparameters were selected using Bayesian Optimization (BO) and trained in the model, which was later utilized for feature extraction. The self-attention extracted features are optimized using a proposed FEcPFA. The best features are selected using FEcPFA and passed to the machine learning classifiers for the final classification. The experimental process was conducted on a publically available MRI dataset and obtained an improved accuracy of 99.9%. The results were compared with state-of-the-art (SOTA) techniques, and the improvement of the proposed framework (accuracy and time) was shown.