Impact of using different brain layer amounts on the accuracy of Convolutional Neural networks trained on MR-Images to identify Parkinson's Disease

Sammanfattning: Parkinson’s Disease (PD) is a neurodegenerative disease and brain disorder which affects the motor system and leads to shaking, stiffness, impaired balance and coordination. Diagnosing PD from Magnetic resonance images (MR-images) is difficult and often not possible for medical experts and therefore Convolutional neural networks (CNNs) are used instead. CNNs can detect small abnormalities in the MR-images that can be insignificant and undetectable for the human eye and this is the reason they are widely used in PD diagnosis with MR-images. CNNs have traditionally been trained on image data where PD affected brain areas (called brain slices) are converted into images first. Using this method, other large areas of the brain which might also be affected by PD are missed because it is not possible to combine more than 3 brain slices into the color channels of an image for training. This study aims to create a CNN and train it on larger parts of the brain and compare the accuracy of the created CNN when it is trained on different amounts of brain slices. The study then investigates if there is an optimal amount of brain area that produces the highest accuracy in the created CNN. During the study, we gathered results which show that, for our dataset, the accuracy increases when more brain slices are used. The trained CNN in this study reaches a maximum accuracy of 75% when it is trained on 7 slices and an accuracy of 60% when it is trained on a single slice. Training on 7 slices results in a significant improvement over training on a single slice. We believe that these 7 slices of brain contain a brain region called basal ganglia which is affected by PD and this is the reason that our CNN achieves the highest accuracy at 7 brain slices. We concluded that an optimal brain slice amount can be found which can increase the accuracy of the network by a considerable amount but this process takes a lot of time.