Detection of Parkinson’s disease from Neuro-imagery using deep neural network with transfer learning

Abstract

Parkinson’s disease is a neurological condition that is dynamic and steadily influences the movement of the human body. It causes issues within the brain and slowly increments time by time. Tremor is the major side effect of PD where the entire body begins shaking. Besides, a person’s muscle may end up rigid or stiff and it may happen any portion of his body. PD influences the central apprehensive system which is happening because of the hardship of dopaminergic neurons brought about in a neuro-degenerative incubation. It is grouped beneath advancement clutter as patients who have PD appear with tremor, unyielding nature, postural shifts, and lessen in unconstrained advancements. There is no particular diagnosis process for PD. PD varies from one person to another person and the situation and history. MRI, CT, ultrasound of the brain, PET scans are common imaging tests to figure out this disease but these tests are not particularly effective. In this research, several tests ran on two types of data group - control and PD affected people. The dataset is collected from the Parkinson’s Progression Markers Initiative (PPMI) repository. Then MRI slices are processed from selected data group into the CNN models. Three CNN models are sent into this thesis work to extract features from the data group. The CNN models are InceptionV3, VGG16 and VGG19. These models are used in this research to compare and get better accuracy. Among these models VGG19 worked best in the dataset because the accuracy for VGG19 is 91.5% where VGG16 gives 88.5% and inceptionV3 gives 89.5% on detecting PD.