image thumbnail

Synthetic skin lesion image generation using GANs

version 1.01 (598 MB) by Oge Marques
Example of how to use MATLAB to generate synthetic images of skin lesions.

24 Downloads

Updated 29 Jul 2021

From GitHub

View license on GitHub

View Synthetic skin lesion image generation using GANs on File Exchange

Synthetic skin lesion image generation using GANs

This repository shows an example of how to use MATLAB to generate synthetic images of skin lesions.

The training data set consists of annotated images from the ISIC 2016 challenge, Task 3 (Lesion classification) data set, containing 900 dermoscopic lesion images in JPEG format1.

The code is based on an example using the flowers dataset available online.

Snapshot of the GAN after training. (L) generated images; (R) generator (blue) and discriminator (red) curves showing score (between 0 and 1, where 0.5 is best) for each iteration.
Examples of synthetically generated images.

Requirements

Suggested steps

  1. Download or clone the repository.
  2. Open MATLAB.
  3. Edit the contents of the imageFolder variable in the skin_lesion_gan.mlx file to reflect the path to your selected dataset.
  4. Run the skin_lesion_gan.mlx script and inspect results.

Additional remarks

  • You are encouraged to expand and adapt the example to your needs.
  • The choice of network architectures for both the generator and discriminator was inspired by the DCGAN.
  • The choice of hyperparameters (learning rate, mini-batch size, number of epochs, etc.) is merely illustrative. You are encouraged to (use Experiment Manager to) tweak those choices and find a better solution 2.

Notes

[1] This example uses a fairly small subset of images to make it easier to get started without having to worry about large downloads and long training times.

[2] See this for ideas and example code for using MATLAB Experiment Manager.

Cite As

Oge Marques (2021). Synthetic skin lesion image generation using GANs (https://github.com/ogemarques/gan-skin-matlab/releases/tag/1.01), GitHub. Retrieved .

MATLAB Release Compatibility
Created with R2021a
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
To view or report issues in this GitHub add-on, visit the GitHub Repository.
To view or report issues in this GitHub add-on, visit the GitHub Repository.