Abstract
Background/Objectives: Alzheimer's disease (AD) is the leading cause of dementia and is characterized by progressive neurodegeneration, resulting in cognitive impairment and structural brain changes. Although no curative treatment exists, pharmacological therapies like cholinesterase inhibitors and NMDA receptor antagonists may deliver symptomatic relief and modestly delay disease progression. Structural magnetic resonance imaging (sMRI) is a commonly utilized modality for the diagnosis of brain neurological diseases and may indicate abnormalities. However, improving the recognition of discriminative characteristics is the primary difficulty in diagnosis utilizing sMRI. Methods: To tackle this problem, the Fuzzy Optimized Attention Network with Multi-Instance Deep Learning (FOA-MIDL) system is presented for the prodromal phase of mild cognitive impairment (MCI) and the initial detection of AD. Results: An attention technique to estimate the weight of every case is presented: the fuzzy salp swarm algorithm (FSSA). The swarming actions of salps in oceans serve as the inspiration for the FSSA. When moving, the nutrient gradients influence the movement of leading salps during global search exploration, while the followers fully explore their local environment to adjust the classifiers' parameters. To balance the relative contributions of every patch and produce a global distinct weighted image for the entire brain framework, the attention multi-instance learning (MIL) pooling procedure is developed. Attention-aware global classifiers are presented to improve the understanding of the integral characteristics and form judgments for AD-related categorization. The Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Australian Imaging, Biomarker, and Lifestyle Flagship Study on Ageing (AIBL) provided the two datasets (ADNI and AIBL) utilized in this work. Conclusions: Compared to many cutting-edge techniques, the findings demonstrate that the FOA-MIDL system may determine discriminative pathological areas and offer improved classification efficacy in terms of sensitivity (SEN), specificity (SPE), and accuracy.