A Hybrid-Layered Framework for Detection and Diagnosis of Alzheimer’s Disease (AD) from Fundus Images

Alzheimer’s disease (AD) is the most common disease that can cause a brain disorder in a human aged above 65. Detecting and diagnosing AD becomes a more complicated and complex task by using various manual processes. DL and ML algorithms are most widely used to analyze the complex features from the medical data used to detect AD from various samples. Several types of sample formats are used to detect AD. This paper mainly focused on detecting the AD from the retinal fundus images. Analyzing the early symptoms of AD can prevent the patient’s life from permanent eye loss. ML algorithms are having various drawbacks that use complex computations and more computation time for the processing of data. The AD prediction is done by using the fundus color images collected from the Kaggle dataset. ML follows various steps to complete the task such as training, pre-processing and algorithm implementation. In the existing approaches, a limited number of parameters are used. Another disadvantage of the traditional algorithms shows the low accuracy and unmatched results. This paper introduced the hybrid-layered framework is developed to detect the AD from the fundus images dataset. Several performance metrics such as precision, recall, F1-score, and accuracy are used to show the results.