Extreme Points Derived Confidence Map as a Cue for Class-Agnostic Interactive Segmentation Using Deep Neural Network

Overview

This repository is the PyTorch implementation for our paper Extreme Points Derived Confidence Map as a Cue for Class-Agnostic Interactive Segmentation Using Deep Neural Network, to be published at MICCAI 2019.

Dependencies

1. PyTorch 1.1.0
2. Python 3.6
3. Pydicom 1.2.2

Citation

Please cite the following work if you use this package.

@article{Inproceedings,
    title = {{Extreme Points Derived Confidence Map as a Cue For Class-Agnostic Segmentation Using Deep Neural Network}},
    booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
    author = {Khan, Shadab and Shahin, Ahmed H. and Villafruela, Javier and Shen, Jianbing and Shao, Ling},
    year={2019}
}

Acnowledgement

We thank the authors of DEXTR-PyTorch and pytorch-deeplab-resnet for making their PyTorch implementation of DEXTR and DeepLab-v2 available!

Contact

Please contact Shadab Khan (skhan.shadab@gmail.com) or Ahmed Shahin (ahmedhshahen@gmail.com) for any further inqueries.