Asia-Pacific Journal of Neural Networks and Its Applications
| Volume 2, No. 2, 2018, pp 13-18 | ||
| Abstract |
An Automatic Diagnostic Algorithm for Parkinson’s Disease Based on Deep Learning
|
|
Abstract
Magnetic resonance imaging (MRI) of the midbrain is the primary tool to diagnose Parkinson’s disease (PD). However, it is difficult to diagnose PD based on MR images manually. Therefore, we developed an automatic diagnostic algorithm for PD that was based on deep learning. The algorithm is composed of two neural networks. The first one is the Faster R-CNN that identifies the areas that may be used for PD diagnosis from midbrain MR images. The second one is the CNN that we defined, which classifies the areas identified in the first network. The test results showed that our algorithm had a fairly high accuracy in PD diagnosis.