Alzheimer’s Disease is a severe neurological brain disorder. It destroys brain cells causing people to lose their memory, mental functions and ability to continue daily activities. Alzheimer’s Disease is not curable, but earlier detection can help improve symptoms in a great deal. Machine learning techniques can vastly improve the process for accurate diagnosis of Alzheimer’s Disease. In recent days deep learning techniques have achieved major success in medical image analysis. But relatively little investigation has been done to applying deep learning techniques for Alzheimer’s Disease detection and classification. We presents a novel deep learning model for multi-Class Alzheimer’s Disease detection and classification using Brain MRI Data. We design a very deep convolutional network and demonstrate the performance on The Alzheimer's Disease Neuroimaging Initiative (ADNI) database.
VGG19, DenseNet121, SqueezeNet architectures, Data Augmentation such as zoom,rotation. The ADNI dataset is a publicly available dataset that includes clinical, imaging, and genetic data from over 1,500 participants with normal cognition, mild cognitive impairment (MCI), and AD.
VGG19 and DenseNet121 performed the greatest in predicting.
VGG19 achieved Accuracy = 83.2%, AUC = 96.6%, Precision= 85.0%, Recall= 80.8%
DenseNet121 achieved Accuracy=79.8%, AUC = 95.7%, Precision= 82.1%, Recall= 78.0% values for the test.
SqueezeNet had the lowest accuracy in predicting. Overall VGG19 improved the performance values