Synthetic skin lesion image generation using GANs

버전 1.01 (598 MB) 작성자: Oge Marques
Example of how to use MATLAB to generate synthetic images of skin lesions.
다운로드 수: 186
업데이트 날짜: 2021/7/29

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.

인용 양식

Oge Marques (2024). Synthetic skin lesion image generation using GANs (https://github.com/ogemarques/gan-skin-matlab/releases/tag/1.01), GitHub. 검색됨 .

MATLAB 릴리스 호환 정보
개발 환경: R2021a
모든 릴리스와 호환
플랫폼 호환성
Windows macOS Linux

Community Treasure Hunt

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

Start Hunting!
버전 게시됨 릴리스 정보
1.01

See release notes for this release on GitHub: https://github.com/ogemarques/gan-skin-matlab/releases/tag/1.01

1.0

이 GitHub 애드온의 문제를 보거나 보고하려면 GitHub 리포지토리로 가십시오.
이 GitHub 애드온의 문제를 보거나 보고하려면 GitHub 리포지토리로 가십시오.