Git Product home page Git Product logo

task-aug's Introduction

Domain Generalization on Medical Imaging Classification Using Episodic Training with Task Augmentation (CBM 2021) (Link)

A Pytorch Implementation of ''Domain Generalization on Medical Imaging Classification Using Episodic Training with Task Augmentation'', which is accepted by the jounal of Computers in Biology and Medicine.

Requirements

  • Python == 3.7.4
  • Tensorflow == 1.14.0
  • CUDA 8.0

Epithelium-stroma classification

Dataset

You can download the annotated pathological datasets of VGH, NKI, IHC and NCH from here.

Train

python main_mame.py

Test

python test_mame.py

Liver segmentation

Train

python main_seg_mame.py

Test

python test_seg_mame.py

Results on epithelium-stroma classification

Source Target MLDG Epi-FCR MetaReg JiGen MASF Ours
NKI,IHC,NCH VGH 91.13 91.49 91.74 92.05 92.43 93.51

Results on liver segmentation

Source Target MLDG Epi-FCR MetaReg JiGen MASF Ours
BTCV,CHAOS,LITS IRCAD 89.17 89.26 89.17 91.44 90.89 92.14

Citation

If you find this repository useful, please cite our paper:

@article{li2022domain,
  title={Domain generalization on medical imaging classification using episodic training with task augmentation},
  author={Li, Chenxin and Lin, Xin and Mao, Yijin and Lin, Wei and Qi, Qi and Ding, Xinghao and Huang, Yue and Liang, Dong and Yu, Yizhou},
  journal={Computers in Biology and Medicine},
  volume={141},
  pages={105144},
  year={2022},
  publisher={Elsevier}
}

task-aug's People

Contributors

xggnet avatar yijinmao avatar

Watchers

avatar

Forkers

yijinmao

task-aug's Issues

How to perform data loading

Thanks for your code! I'm trying to reproduce your results but the data loading step is missing. You load scan slices from e.g LIVER/{challenge}.txt which lists "...{challenge}/case{XXX}/image{XXX}.jpg". However this is not the original format of the data. Is this pre-processed already? Which slices do they correspond to? Is there any information regarding data pre-processing?

Checkpoints release

Thanks for your paper "Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation": I found it very interesting and motivating! We were thinking of using it for our current task: abdominal organ segmentation in the wild. Can you provide us the checkpoints (model weights) of your trained models (on the 4 mentioned experiments of Table 4)?

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.