A Hybrid Deep Learning Framework for Early Diagnosis of Alzheimer's Disease

Alzheimer's Disease(AD) is a slowly progressing disease that ultimately damages the brain cells. During the initial stage of Alzheimer's disease (AD), a precise diagnosis is very important for patient care, as at this stage action can be taken to slow down the process of any type of irreversible brain damage. Machine learning methods were applied by various researchers to detect AD. The medical imaging shows promising diagnosis on verifying it with the deep learning technique disease. This article proposed a hybrid model using transfer learning and Decision Trees DT. The features of transfer learning models i.e. Mobilenet and Densenet121 are used as input by DT. The final classification is done by DT and the results are evaluated on various metrics such as accuracy, precision, recall, etc. Our proposed hybrid model performs significantly better compared with the individual transfer learning models.