Optimized Alzheimer disorder classification with DACN-MFFN utilizing OBLDE-TDO enhanced deep neural network features

Abstract

Alzheimer’s disease (AD) is a condition that causes the progressive deterioration of the brain and has important consequences for society and healthcare. Therefore, it is crucial to diagnose the disease early and accurately in order to effectively manage it. This work introduces a new method for predicting AD by utilising advanced Deep Learning (DL) models and optimised strategies for extracting features. The Dual Attention-based Convolutional Network combined with Multilayer Feature Fusion Network (DACN-MFFN), optimised using the Opposition Based Learning Differential Evaluation combined with Tasmanian Devil Optimization (OBLDE-TDO) technique, exhibits outstanding performance in accurately categorising AD patients. The tests are performed using a publically accessible MRI dataset from Kaggle, implementing a 70:30 split for training and testing. The performance of the model is assessed using conventional measures such as accuracy, precision, recall, and F1 score, in addition to considering its computational complexity. The results demonstrate that the proposed model obtains an exceptional accuracy of 99.6% in predicting AD, outperforming the most advanced models currently available. Furthermore, the model exhibited exceptional precision, recall, and F1 score metrics, underscoring its effectiveness in differentiating between instances of AD and non-AD cases. The model demonstrated a notable success in minimising misunderstandings, as evidenced by its low False Negative Rate of 1%. In addition, our ablation investigation shown that the proposed model is very responsive to fine-tuning of hyperparameters, achieving optimal performance with certain learning rates and a variety of drop out rates and weight decay ratios. By doing meticulous optimisation, combinations that achieve a harmonious equilibrium between the performance of the model and its computational efficiency were discovered, thus proving its efficacy for diagnosing AD early and accurately.