Overview / Usage

Parkinson’s disease is a nervous system disorder that affects movement. The disease is progressive and is marked by five different stages. Although I am aware of the disease, I had not heard of the geometric drawing test. There is a 2017 paper, Distinguishing Different Stages of Parkinson’s Disease Using Composite Index of Speed and Pen-Pressure of Sketching a Spiral, by Zham et al.

The researchers found that the drawing speed was slower and the pen pressure lower among Parkinson’s patients — this was especially pronounced for patients with a more acute/advanced forms of the disease.

One of the symptoms of Parkinson’s is tremors and rigidity in the muscles, making it harder to draw smooth spirals and waves.

Joao Paulo Folador, a Brazillian Ph.D.student postulated that it might be possible to detect Parkinson’s disease using the drawings alone rather than having to measure the speed and pressure of the pen on paper.

Reducing the requirement of tracking pen speed and pressure:

1. Eliminates the need for additional hardware when performing the test.
2. Makes it far easier to automatically detect Parkinson’s.

Hence, the idea of this project - to build a deep learning system to take an image of a spiral/wave test and to tell if the corresponding person is suffering from Parkinson's disease or not.

Methodology / Approach

• Created an image bunch of size 256*256 so that the deep learning models could be provided with as much as pixel information possible
• Applied data augmentation for better generalization
• Used a pretrained ResNet34 architecture and fine-tuned it to aid the performance
• Created interpretation plots to help the viewers discover more about the data and model's performance

Technologies Used

• Python (language)
• fastai, numpy (main libraries)
• Google Colab (environment)

Repository

https://github.com/sayakpaul/Parkinson-s-Disease-Classifier/