mRMR-based hybrid convolutional neural network model for classification of Alzheimer's disease on brain magnetic resonance images

Alzheimer's disease is a progressive neurodegenerative fatal disease characterized by a decrease in mental functions. Although there is no definitive treatment for the disease, there are some treatment methods that delay the course of the disease in case of early diagnosis. Therefore, early diagnosis and classification of the disease are important to determine the most appropriate treatment. The most commonly used method for imaging the brain with a high soft-tissue resolution is magnetic resonance imaging (MRI). Brain MRI help in the diagnosis of Alzheimer's disease with some specific imaging findings. In this study, we aimed to classify Alzheimer's disease in brain MRI using machine learning architectures. An mRMR-based hybrid CNN was proposed in the study. First, features of MRI in Darknet53, InceptionV3, and Resnet101 models were extracted. These extracted features were concatenated. Then the obtained features were optimized using the mRMR method. SVM and KNN classifiers were used to classify the optimized features. The accuracy value obtained in the proposed model was 99.1%.

Automated summary

Alzheimer's disease is a progressive neurodegenerative disorder, with MRI imaging playing a key role in diagnosis. This study proposed a machine learning approach for classifying Alzheimer's disease in brain MRI, achieving a high accuracy rate of 99.1%.