Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Dataset containing epidemiological, clinical and imaging data from 55 patients suffering from Parkinson's Disease, as well as 23 Normal Control subjects.

License

Notifications You must be signed in to change notification settings

djib2011/ntua-parkinson-dataset

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 

Repository files navigation

The NTUA Parkinson Dataset

Note:
The dataset is hosted in a separate git repository. Follow the link to see in structions on how to download the dataset.

This dataset currently consists of MRI and DaT Scan examinations from a total of 78 individuals. Out of those 55 are suffering from Parkinson's Disease (PD), while 23 serve as normal control subjects (NPD).

A total of over 42000 images are available for academic use.

Image type PD NPD Total
DaT scan 590 330 920
MRI 32706 10381 43087

More information on the dataset can be found here.

If you plan to use this dataset in your research, please cite:

@article{tagaris2018machine,
  title={Machine Learning for Neurodegenerative Disorder Diagnosis—Survey of Practices and Launch of Benchmark Dataset},
  author={Tagaris, Athanasios and Kollias, Dimitrios and Stafylopatis, Andreas and Tagaris, Georgios and Kollias, Stefanos},
  journal={International Journal on Artificial Intelligence Tools},
  volume={27},
  number={03},
  pages={1850011},
  year={2018},
  publisher={World Scientific}
}

This dataset has been used in the following research studies: 1, 2, 3, 4.

Important Note

The original dicom images are not available as they contain some sensitive information in the form of metadata. To process the dicom files and anonymize them, the thicom package was developed.

About

Dataset containing epidemiological, clinical and imaging data from 55 patients suffering from Parkinson's Disease, as well as 23 Normal Control subjects.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published