Skip to content

We proposed a novel U-Net-based model -- DC-UNet to do medical image segmentation.

Notifications You must be signed in to change notification settings

AngeLouCN/DC-UNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

61 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DC-UNet: Rethinking the U-Net Architecture with Dual Channel Efficient CNN for Medical Images Segmentation

Result
This repository contains the implementation of a new version U-Net (DC-UNet) used to segment different types of biomedical images. This is a binary classification task: the neural network predicts if each pixel in the biomedical images is either a region of interests (ROI) or not. The neural network structure is described in this

paper.

🔥 NEWS 🔥 The pytorch version is available pytorch-version.

Architecture of DC-UNet

DC-BlockRes-path
DC-UNet

Dataset

In this project, we test three datasets:

  • Infrared Breast Dataset
  • Endoscopy (CVC-ClinicDB)
  • Electron Microscopy (ISBI-2012)

Usage

Prerequisities

The following dependencies are needed:

  • Kearas == 2.2.4
  • Opencv == 3.3.1
  • Tensorflow == 1.10.0
  • Matplotlib == 3.1.3
  • Numpy == 1.19.1

training

You can download the datasets you want to try, and just run:

main.py

Results on three datasets

Result_table

Citation

If you think this work and code is helpful in your research, please cite:

@inproceedings{lou2021dc,
  title={DC-UNet: rethinking the U-Net architecture with dual channel efficient CNN for medical image segmentation},
  author={Lou, Ange and Guan, Shuyue and Loew, Murray H},
  booktitle={Medical Imaging 2021: Image Processing},
  volume={11596},
  pages={115962T},
  year={2021},
  organization={International Society for Optics and Photonics}
}

@inproceedings{lou2019segmentation,
  title={Segmentation of Infrared Breast Images Using MultiResUnet Neural Networks},
  author={Lou, Ange and Guan, Shuyue and Kamona, Nada and Loew, Murray},
  booktitle={2019 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)},
  pages={1--6},
  year={2019},
  organization={IEEE}
}

About

We proposed a novel U-Net-based model -- DC-UNet to do medical image segmentation.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages