Skip to main content

Deep Learning Framework For Medical Image Analysis

Project description

SAMITorch

Welcome to SAMITorch

Build Status GitHub All Releases GitHub issues GitHub GitHub contributors

SAMITorch is a deep learning framework for Shape Analysis in Medical Imaging laboratory of École de technologie supérieure using PyTorch library. It implements an extensive set of loaders, transformers, models and data sets suited for deep learning in medical imaging. Our objective is to build a tested, standard framework for quickly producing results in deep learning reasearch applied to medical imaging.

Table Of Contents

Authors

References

Segmentation

@article{RN10,
   author = {Çiçek, Özgün and Abdulkadir, Ahmed and Lienkamp, Soeren S. and Brox, Thomas and Ronneberger, Olaf},
   title = {3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation},
   journal = {eprint arXiv:1606.06650},
   pages = {arXiv:1606.06650},
   url = {https://ui.adsabs.harvard.edu/\#abs/2016arXiv160606650C},
   year = {2016},
   type = {Journal Article}
}

Classification

@inproceedings{RN12,
   author = {He, K. and Zhang, X. and Ren, S. and Sun, J.},
   title = {Deep Residual Learning for Image Recognition},
   booktitle = {2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
   pages = {770-778},
   ISBN = {1063-6919},
   DOI = {10.1109/CVPR.2016.90},
   type = {Conference Proceedings}
}

Diffusion imaging

Application

Setup

pip install -r [path/to/requirements.txt]
python3 <main_script>.py

Project architecture

Folder structure

├── configs                 - This folder contains the YAML configuration files.
│   ├── train.yaml                  - This file contains your training configuration. MUST be a YAML file.
│   └── test.yaml                   - OPTIONAL. This file contains the testing configuration. MUST be a YAML file.
|
├── docker                  - Contains Dockerfile needed to provide a functional Docker environment for your publication.
|   └── dockerfile
|
├── icons                   - Contains project's artwork.
|
├── initializers            - This folder contains custom layer/op initializers.  
|   └── base_initializer.py
│
├── inputs                  - This folder contains anything relative to inputs to a network.
|   └── transformers.py  
|
├── metrics                  - This folder contains various metrics used to measure a training session of a model.
|   ├── gauges.py 
|   └── metrics.py
|   
├── models                  - This folder contains any standard and tested deep learning models.
│   └── base_model.py                      
|
├── preprocessing           - This folder contains anything relative to input preprocessing, and scripts that must be executed prior training.
|
├── tests                   - Folder containing unit tests of the standard framework api and functions.
|   
├── training                - This folder contains trainers.
│   ├── base_trainer.py 
|   ├── losses.py  
|   └── trainer.py
│  
└── utils                   - This folder contains any utils you need.
     └── utils.py

Main components

(To be documented shortly...)

Models

Trainers

Transformers

Logger

Configs

Main

Contributing

If you find a bug or have an idea for an improvement, please first have a look at our contribution guideline. Then,

  • Create a branch by feature and/or bug fix
  • Get the code
  • Commit and push
  • Create a pull request

Branch naming

Instance Branch Description, Instructions, Notes
Stable stable Accepts merges from Development and Hotfixes
Development dev/ [Short description] [Issue number] Accepts merges from Features / Issues and Hotfixes
Features/Issues feature/ [Short feature description] [Issue number] Always branch off HEAD or dev/
Hotfix fix/ [Short feature description] [Issue number] Always branch off Stable

Commits syntax

Adding code:

+ Added [Short Description] [Issue Number]

Deleting code:

- Deleted [Short Description] [Issue Number]

Modifying code:

* Changed [Short Description] [Issue Number]

Merging branches:

Y Merged [Short Description]

Acknowledgment

Thanks to École de technologie supérieure, Hervé Lombaert and Christian Desrosiers for providing us a lab and helping us in our research activities.

Icons made by Freepik from www.flaticon.com is licensed by CC 3.0 BY

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

SAMITorch-0.1.56.tar.gz (58.0 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page