Automated wound image segmentation: transfer learning from human to pet via active semi-supervised learning

An automated pipeline capable of segmenting wound images of animals. Active Semi-Supervised Learning techniques were applied for human-wound images to perform segmentation, then the same models were trained, via Transfer Learning, adopting an Active Semi-Supervised Learning to unlabelled animal-wound images.
Report bug · Request feature

Table of contents

• Quick start
• What's included
• Bugs and feature requests
• Contributing
• Creators
• Thanks
• Copyright and license

Quick start

The frameworks used in this project are

• segmentation models
• TensorFlow 2.8.0

What's included

All the available files are structured as follows:

• read_models.ipynb is a notebook for fast model loading;
• models contains the 4 model produced in the study

Automated-wound-image-segmentation/
├──read_models.ipynb
└──models/
    ├──efficientnet_deepskin_human.h5
    ├──efficientnet_petwound_animal.h5
    ├──mobilenet_deepskin_human.h5
    └──mobilenet_petwound_animal.h5 
     

Bugs and feature requests

Have a bug or a feature request? Please first read the issue guidelines and search for existing and closed issues. If your problem or idea is not addressed yet, please open a new issue.

Contributing

Please read through our contributing guidelines. Included are directions for opening issues, coding standards, and notes on development.

Moreover, all HTML and CSS should conform to the Code Guide, maintained by Main author.

Editor preferences are available in the editor config for easy use in common text editors. Read more and download plugins at https://editorconfig.org/.

Creators

Creator 1

• https://github.com/Torbidos7/

Thanks

Thank you for coming 😝

Copyright and license

Code and documentation copyright 2011-2018 the authors. Code released under the MIT License.