Publication

Abstract : Alzheimer’s is the most common form of dementia in older individuals, which presents a global health challenge with 10 million new cases annually. This neurological disorder causes neurodegenerative alterations in the brain to unfold gradually, commencing with mild memory impairment and then escalating to loss of social interaction and awareness of the environment. Alzheimer Disease International (ADI) believes that 75% of dementia cases globally go undetected, making the early diagnosis challenging. Currently, stopping the development of Alzheimer’s disease is difficult since there are no viable diagnosis and treatment solutions available. To overcome these challenges, there is now great interest in using machine learning (ML) for early diagnosis of metabolic disorders such as Alzheimer’s. In this work, we propose utilizing a deep convolutional neural network to detect the different phases of Alzheimer’s disease using brain MRI structural data analysis. Magnetic resonance imaging (MRI) aids in the early detection of Alzheimer’s disease and achieves greater efficacy for initial-stage detection. Clinicians can use the suggested categorization approach to diagnose these disorders much earlier. With these ML algorithms, it is highly advantageous to reduce yearly death rates of Alzheimer’s disease in early diagnosis. The suggested technique achieves improved results, with an approved mean score of 96.1% on Alzheimer’s Disease test data. Compared to previous efforts, the current score for accuracy is much greater.