Skip to content

[TMI'20] Learn to Threshold: ThresholdNet with Confidence-Guided Manifold Mixup for Polyp Segmentation

License

Notifications You must be signed in to change notification settings

Guo-Xiaoqing/ThresholdNet

Repository files navigation

Learn to Threshold: ThresholdNet with Confidence-Guided Manifold Mixup for Polyp Segmentation

by Xiaoqing Guo.

Summary:

Intoduction:

This repository is for our IEEE TMI paper "Learn to Threshold: ThresholdNet with Confidence-Guided Manifold Mixup for Polyp Segmentation"

Framework:

Usage:

Requirement:

Pytorch 1.3 Python 3.6

Preprocessing:

Clone the repository:

git clone https://github.com/Guo-Xiaoqing/ThresholdNet.git
cd ThresholdNet 
bash Threshold.sh

Data preparation:

Dataset should be put into the folder './data'. For example, if the name of dataset is CVC, then the path of dataset should be './data/CVC/', and the folder structure is as following.

ThresholdNet
|-data
|--CVC
|---images
|---labels
|---train.txt
|---test.txt
|---valid.txt

The content of 'train.txt', 'test.txt' and 'valid.txt' should be just like:

26.png
27.png
28.png
...

Pretrained model:

You should download the pretrained model from Google Drive, and then put it in the './model' folder for initialization.

Well trained model:

You could download the trained model from Google Drive, which achieves 87.307% in Dice score on the EndoScene testing dataset. Put the model in directory './models'.

Baseline model:

We also provide some codes of baseline methods, including polyp segmentation models and mixup related data augmentation baselines.

Results:

Log files are listed in log.out and log1.out.

Citation:

@article{guo2020learn,
  title={Learn to Threshold: ThresholdNet with Confidence-Guided Manifold Mixup for Polyp Segmentation},
  author={Guo, Xiaoqing and Yang, Chen and Liu, Yajie, Yuan, Yixuan},
  journal={IEEE Transactions on Medical Imaging},
  year={2020},
  volume={40},
  number={4},
  pages={1134-1146},
  publisher={IEEE}
}

Questions:

Please contact "xiaoqingguo1128@gmail.com"

About

[TMI'20] Learn to Threshold: ThresholdNet with Confidence-Guided Manifold Mixup for Polyp Segmentation

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published