saeedizadi / unet_theano

Generative adversarial networks to segment skin lesions

Abstract

The accuracy of skin lesion segmentation has increased in recent years, thanks to advances in machine learning techniques and a large influx of dermoscopy images. However, there is still room for improvement as there exist many considerable challenges mainly due to the large variability in the appearance of lesions (i.e., shape, size, texture, and occlusions). In this work, we present a novel approach for skin lesion segmentation through leveraging generative adversarial networks. Our approach consists of two models: a fully convolutional neural network designed to synthesize an accurate skin lesion segmentation mask (the segmenter), and a convolutional neural network that distinguishes between synthetic and real segmentation masks (the critic).

Keywords

Segmentation, Skin lesion segmentation, Deep learning

Cite

If you use our code, please cite our paper: Generative adversarial networks to segment skin lesions

The corresponding bibtex entry is:

@inproceedings{izadi2018generative,
  title={Generative adversarial networks to segment skin lesions},
  author={Izadi, Saeed and Mirikharaji, Zahra and Kawahara, Jeremy and Hamarneh, Ghassan},
  booktitle={2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)},
  pages={881--884},
  year={2018},
  organization={IEEE}
}