Accurate diagnosis of dementia and Alzheimer's with deep network approach based on multi-channel feature extraction and selection

Abstract

In this article, we have proposed a multi-stage in-depth approach based on the improved VGGNet architecture for automatically and accurately diagnosing dementia and Alzheimer's disease. In this approach, first of all, the learned weights of the VGG16 architecture are frozen, and multichannel attributes are extracted from each pooling layer. Then, these attributes were given to the inputs of the attribute average pooling layers, and one-dimensional attributes were produced using the flattened layer. Distinctive and effective attributes were selected from these deep attributes by the mRMR algorithm. Finally, the selected attributes are given to the input of the eight-layer classification model, which includes the Fully connected, Relu, and softmax layers. A publicly available data set consisting of four classes and 6400 images was used to test the correctness of the proposed architecture. In addition, since the number of images belonging to the classes in this data set is unstable, data augmentation methods were used. As a result, a 98.6% accuracy score was produced with the developed architecture. These results show that the proposed architecture outperforms the original VGG16 and previous works.