SECURED's Synthetic Data Generation library for generating synthetic medical data including mammograms, chest X-rays, CTGs, and MRIs. It aims to provide data that is statistically similar to the original data but does not convey information from the original data. This library can produce data that is similar to the original, but not completely equal to the original data to avoid data leakage. Aside from privacy, synthetic data generation can also be useful as it can be used to complement real data for tasks such as training Machine Learning models, specially Deep Learning models, which require as much data as possible to provide good and generalizable results. The library offers an easy to use interface so that it can be used by coders that might not be aware of how these technologies work. Please, read the README file that comes with the library for further instructions.

This tool is web-based. Once the application is running, the user can access it through the web browser, where they are presented with the parameters for the generation. The user can then fine tune the parameters as they seem fit and then click on “Generate Images”. Mind that it takes some time to generate the images.

Finally, the user is presented with the generated samples they have generated and they will be able to save them to their computer.

Currently, the tool only provides mammogram generation, but we are going to cover soon:

• Cardiotocographies
• Chest X-Ray
• MRI breast/brain interpolation