KLASIFIKASI GANGGUAN KOGNITIF PENYAKIT ALZHEIMER PADA KOMPUTASI PET FLUORODEOXYLUCOSE MRI MENGGUNAKAN MECHINE LEARNING DENGAN METODE CONVOLUTIONAL NEURAL NETWORK

Alzheimer's disease or Alzheimer's Disease (AD) is a brain disease that causes memory loss, decreased ability to think and speak, and changes in behavior. Over time, Alzheimer's disease can make sufferers unable to carry out daily tasks. To detect Alzheimer's disease, doctors perform brain scans such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET). MRI is considered the most important examination in cases of dementia. In this study, the aim is to classify cognitive impairment in Alzheimer's disease using PET Fluorodeoxyglucose (FDG) computational data, measure the performance of the model on the layered structure that has been optimized using hyperparameters (HPO) in terms of accuracy and apply the use of Marchine Learning to classify Alzheimer's disease using using the Convolution Neural Network (CNN) method. This research focuses on designing a classification of connective disorders in Alzheimer's disease, using Convolution Neural Network (CNN) as a method and classification process using Python. In research conducted by researchers, they developed a Convolution Neural Network (CNN) model to classify cognitive disorders in Alzheimer's disease using PET Fluorodeoxyglucose (FDG) data and MRI. The proposed model is able to classify four categories, namely Non Demented, Very Mild Demented, Mild Demented, and Moderate Demented.