|
|
| |
| A Novel Approach for classification of different Alzheimer's stages using pre-trained CNN Models with transferring learning and their comparative analysis
Download PDF
|
Gowhar Mohiuddin Dar, Avinash Bhagat, Sophiya Sheikh
|
Abstract:
Transfer learning has become extremely popular in recent years for tackling issues from various sectors, including the analysis of medical images. Medical image analysis has transformed medical care in recent years, enabling physicians to identify disease early and accelerate patient recovery. Alzheimer's disease diagnosis has been greatly aided by imaging (AD). Alzheimer's is a degenerative neurological condition that slowly deprives patients of their memory and cognitive abilities. Computed tomography and brain MRI scans are used to detect dementia in Alzheimer's patients. This research primarily aims to classify AD patients into multiple classes using ResNet50, VGG16, and DenseNet121 as transfer learning along with CNN networks on a large dataset as compared to existing approaches as hence improves classification accuracy. The different stages of Alzheimer's are early mental retardation, mild mental impairment, late mild mental impartment, and final Alzheimer's stage (AD). The novel approach gives results with an accuracy of 96.6%, significantly improved outcomes compared to existing models.
|
|
|
| | |