/Active-Contour-Loss

Implementation of active contour loss function

Primary LanguagePythonMIT LicenseMIT

Active Contour Loss

Implementation of active contour loss function for medical image segmentation based on "Learning Active Contour Models for Medical Image Segmentation" by Chen, Xu, et al.

Introduction

==The arXiv version of this paper will be available soon. ==

Requirements

Tensorflow >= 1.5

Keras >= 2.0

Numpy

Training

A pretrained model might be suggested to use, because somtimes active contour loss function may not be stable in the early steps for training.

Citation

If you find Active-Contour-Loss is useful in your research, please consider to cite:

@inproceedings{chen2019learning,
  title={Learning Active Contour Models for Medical Image Segmentation},
  author={Chen, Xu and Williams, Bryan M and Vallabhaneni, Srinivasa R and Czanner, Gabriela and Williams, Rachel and Zheng, Yalin},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={11632--11640},
  year={2019}
}

Other Re-implementation

...