Deep Learning Based Multilevel Classification of Alzheimer’s Disease using MRI Scans
Manu Raju, M Thirupalani, S Vidhyabharathi, S. Thilagavathi
Abstract
Abstract Alzheimer’s disease is one of the most frequently studied diseases of the nervous system although it has no cure or slowing its progression. There are various options for treating the symptoms of Alzheimer’s disease in different stages and as the disease progresses over time, patients in their various stages need different treatment. Diagnosis of Alzheimer’s in the elderly is quietly difficult and requires representation of a discriminatory factor in isolation due to similar brain patterns and pixel strength. Deep learning strategies are able to learn such representations from the data. In this proposed work we perform multilevel classification of Alzheimer’s disease ie; Mild Demented, Moderate Demented, Non Demented and Very Mild Demented using transfer learning with VGG16 using Fastai. This approach results in 99% predictive accuracy which means a significant increase in accuracy compared to previous studies and clearly demonstrates the effectiveness of the proposed methods.