dumycq / cfpnet-medicine

A keras-based real-time model for medical image segmentation (CFPNet-M)

CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation

This repository contains the implementation of a novel light-weight real-time network (CFPNet-Medicine: CFPNet-M) to segment different types of biomedical images. It is a medical version of CFPNet, and the dataset we used from top to bottom are **DRIVE, ISBI-2012, Infrared Breast, CVC-ClinicDB and ISIC 2018**. The details of CFPNet-M and CFPNet can be found here respectively.

CFPNet-M, CFPNet Paper, DC-UNet and CFPNet Code

Architecture of CFPNet-M

CFP module

CFPNet-M

Dataset

In this project, we test five datasets:

• Infrared Breast Dataset
• Endoscopy (CVC-ClinicDB)
• Electron Microscopy (ISBI-2012)
• Drive (Digital Retinal Image)
• Dermoscopy (ISIC-2018)

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: for UNet, DC-UNet, MultiResUNet, ICNet, CFPNet-M, ESPNet and ENet, the code is in the folder network. For Efficient-b0, MobileNet-v2 and Inception-v3, the code is in the main.py. Choose the segmentation model you want to test and run:

main.py

Segmentation Results of Five datasets

Speed and FLOPs

The code of calculate FLOPs are in main.py, you can run them after training.

Citation

@article{lou2021cfpnet,
  title={CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation},
  author={Lou, Ange and Guan, Shuyue and Loew, Murray},
  journal={arXiv preprint arXiv:2105.04075},
  year={2021}
}

@article{lou2021cfpnet,
  title={CFPNet: Channel-wise Feature Pyramid for Real-Time Semantic Segmentation},
  author={Lou, Ange and Loew, Murray},
  journal={arXiv preprint arXiv:2103.12212},
  year={2021}
}

@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}
}