Skip to content

Latest commit

 

History

History
87 lines (57 loc) · 2.71 KB

README.md

File metadata and controls

87 lines (57 loc) · 2.71 KB
Raw

Boundary-aware Transformers for Skin Lesion Segmentation

Introduction

This is an official release of the paper Boundary-aware Transformers for Skin Lesion Segmentation.

Boundary-aware Transformers for Skin Lesion Segmentation,
Jiacheng Wang, Lan Wei, Liansheng Wang, Qichao Zhou, Lei Zhu, Jing Qin
In: Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021
[arXiv][Bibetex]

News

  • [5/27 2022] We have released a more powerful XBound-Former with clearer concept and codes.
  • [11/15 2021] We have released the point map data.
  • [11/08 2021] We have released the training / testing codes.

Code List

  • Network
  • Pre-processing
  • Training Codes
  • MS

For more details or any questions, please feel easy to contact us by email ([email protected]).

Usage

Dataset

Please download the dataset from ISIC challenge and PH2 website.

Pre-processing

Please run:

$ python src/process_resize.py
$ python src/process_point.py

You need to change the File Path to your own.

Point Maps

For your convenience, we release the processed maps and the dataset division.

Please download them from Baidu Disk (code：kmqr) or Google Drive

The file names are equal to the original image names.

Training

Testing

Download the pretrained weight for PH2 dataset from Google Drive.

$ python test.py --dataset isic2016

Result

Method Dice IoU HD95 ASSD
Lee et al. 0.918 0.843 - -
BAT (paper) 0.921 0.858 - -

Citation

If you find BAT useful in your research, please consider citing:

@inproceedings{wang2021boundary,
  title={Boundary-Aware Transformers for Skin Lesion Segmentation},
  author={Wang, Jiacheng and Wei, Lan and Wang, Liansheng and Zhou, Qichao and Zhu, Lei and Qin, Jing},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages={206--216},
  year={2021},
  organization={Springer}
}