Classification and Segmentation of Alzheimer Disease in MRI Modality using the Deep Convolutional Neural Networks

Authors : Furkan KARAKAYA, Caglar GURKAN, Abdulkadir BUDAK, Hakan KARATAŞ

Pages : 99-105

Doi:10.31590/ejosat.1171810

View : 158 | Download : 12

Publication Date : 2022-09-30

Article Type : Research Paper

Abstract :In the study, classification and segmentation tasks were implemented for analysis of Alzheimer\`s disease. In classification task, 7 different models were tested using transfer learning. The GoogLeNet model achieved the best classification performance with the accuracy of 0.9467, sensitivity of 0.9474, specificity of 0.9811, and F1-score of 0.9467. In segmentation task, U-Net architecture design was used for the segmentation of Alzheimer\`s disease. U-Net model achieved the dice of 0.874, IoU of 0.776, sensitivity of 0.868, specificity of 0.999, precision of 0.879, and accuracy of 0.999. In order to create the pipeline, classification and segmentation models were used together. Consequently, a computer vision-assisted decision support system was created.
Keywords : Alzheimer, Sınıflandırma, Segmentasyon, GoogLeNet, U Net

ORIGINAL ARTICLE URL