PDGAN

For the past two years, I've been working on creating a machine learning model capable of helping neurologists detect Parkinson's Disease. After working with multiple universities and putting more than 5 hours a day on the project, I completed PDGAN, which is able to classify Parkinson's Disease in MRI scans with an accuracy that is far superior to the baseline Neurologist accuracy. PDGAN uses convolutional neural networks for its classification scheme but also is capable of synthetically generating lifelike brain scans to augment the data. I created this arm of the product because I faced a lack of ample training data, and to augment it I had to synthesize my own.