GithubHelp home page GithubHelp logo

deeponcology / colonsegnet Goto Github PK

View Code? Open in Web Editor NEW

This project forked from debeshjha/colonsegnet

0.0 0.0 0.0 26.9 MB

Official implementation of ColonSegNet: Real-Time Polyp Segmentation (Used in NVIDIA Clara Holoscan App for Polyp Segmentation)

Home Page: https://pubmed.ncbi.nlm.nih.gov/33747684/

Python 100.00%

colonsegnet's Introduction

Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning

ColonSegNet

ColonSegNet is an encoder-decoder that uses residual block with squeeze and excitation network as the main component. The network is designed to have very few trainable parameters as compared to other networks baseline networks such as U-Net, PSPNet, DeepLabV3+, and others. The use of fewer trainable parameters makes the proposed architecture a very light-weight network that leads to real-time performance.

Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning.

Architecture

How to run

Please run the files in the following sequence:

  1. data_aug.py - Change the dataset path. This will create a new_data folder containing augmented data.
  2. train.py - If you want to use augmented data from the new_data folder then uncomment the lines from 70-74 and comment the lines 76 and 77.
  3. test.py - Set the proper path for the dataset in line number 55 and run the code. This will provide the scores of different evaluation metrics as well as masks which are saved in the "results" folder.

Dataset:

You can download the Kvasir-SEG from here: https://datasets.simula.no/downloads/kvasir-seg.zip

Scripts for bounding boxes

Note: ColonSegNet is not an end to end network for polyp detection. Basically, it is a segmentation network. We have converted the ground truth masks into bounding boxes. The link for the script can be found below:

https://github.com/sharibox/EAD2019/tree/master/fileFormatConverters

TensorFlow implementation of ColonSegNet

https://github.com/nikhilroxtomar/Semantic-Segmentation-Architecture/blob/main/TensorFlow/colonsegnet.py

Results

Citation

Please cite our paper if you find the work useful:

@article{jha2021real,
  title={Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning},
  author={Jha, Debesh and Ali, Sharib and Tomar, Nikhil Kumar and Johansen, H{\aa}vard D and Johansen, Dag and Rittscher, Jens and Riegler, Michael A and Halvorsen, P{\aa}l},
  journal={Ieee Access},
  volume={9},
  pages={40496--40510},
  year={2021}
}

Contact

Please contact [email protected] and [email protected] for any further questions.

colonsegnet's People

Contributors

debeshjha avatar nikhilroxtomar avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.