Skip to content
guijacquemet edited this page Nov 9, 2021 · 15 revisions

ZeroCostDL4Mic - What is it?

Overview

ZeroCostDL4Mic is a toolbox for the training and implementation of common Deep Learning approaches to microscopy imaging. It exploits the ease-of-use and access to GPU provided by Google Colab.

Training data can be uploaded to the Google Drive from where it can be used to train models using the provided Colab notebooks in a web-browser. Inference (predictions) on unseen data can then also be performed within the same notebook, therefore not requiring any local hardware or software set-up.

Want to see a short video demonstration?

Running a ZeroCostDL4Mic notebook Example data in ZeroCostDL4Mic Romain's talk @ Aurox conference Talk @ SPAOM NEUBIAS webminar

Implemented networks

ZeroCostDL4Mic provides fully annotated Google Colab optimised Jupyter Notebooks for popular pre-existing networks. These cover a range of important image analysis tasks (e.g. segmentation, denoising, restoration, label-free prediction). There are 3 types of implemented networks:

We welcome network contributions from the research community. If you wish to contribute, please read our guidelines first.

How to get the notebooks and test datasets?

Both fully supported and beta-testing versions of the individual notebooks can be directly opened from GitHub into Colab by clicking one of the respective links in the table below. You will need to create a local copy to your Google Drive in order to save and modify the notebooks. Once opened in Colab, follow the instructions described in the specific notebook that you selected to install the relevant packages, load the training dataset, train, check on test datasets and perform inference and predictions on unseen data.

With the exception of the U-net training data, we provide training and test datasets that were generated by our labs. These can be downloaded from Zenodo using the various links below. The U-net data was obtained from the ISBI segmentation contest.

Segmentation networks

Network Paper(s) Tasks Status Link to example training and test dataset Direct link to the notebook in Colab
U-Net (2D) here and here Binary segmentation Fully supported here Open In Colab
U-Net (3D) here Binary segmentation Fully supported EPFL dataset Open In Colab
U-Net (2D) multilabel here and here Semantic segmentation Under beta-testing here Open In Colab
DenoiSeg here Joint denoising and binary segmentation Fully supported Available soon Open In Colab
StarDist (2D) here and here Instance segmentation Fully supported here Open In Colab
StarDist (3D) here and here Instance segmentation Fully supported from Stardist github Open In Colab
Cellpose (2D and 3D) here Instance segmentation (Cells or Nuclei) Fully supported Coming soon! Open In Colab
SplineDist (2D) here Instance segmentation Fully supported here Open In Colab
EmbedSeg (2D) here Instance segmentation Under beta-testing here Open In Colab
MaskRCNN (2D) here Instance segmentation Under beta-testing Coming soon! Open In Colab
Interactive Segmentation - Kaibu (2D) here Interactive instance segmentation Under beta-testing Coming soon! Open In Colab

Denoising and image restoration networks

Network Paper(s) Tasks Status Link to example training and test dataset Direct link to the notebook in Colab
Noise2Void (2D) here Self-supervised denoising Fully supported here Open In Colab
Noise2Void (3D) here Self-supervised denoising Fully supported here Open In Colab
CARE (2D) here Supervised denoising Fully supported here Open In Colab
CARE (3D) here Supervised denoising Fully supported here Open In Colab
3D-RCAN here Supervised denoising Under beta-testing here Open In Colab
DecoNoising (2D) here Self-supervised denoising Under beta-testing here Open In Colab

Super-resolution microscopy networks

Network Paper(s) Tasks Status Link to example training and test dataset Direct link to the notebook in Colab
Deep-STORM here Single Molecule Localization Microscopy (SMLM) image reconstruction from high-density emitter data Fully supported Training data simulated in the notebook or available from here Open In Colab
DFCAN here image upsampling Under beta-testing here Open In Colab

Object detection networks

Network Paper(s) Tasks Status Link to example training and test dataset Direct link to the notebook in Colab
YOLOv2 here Object detection (bounding boxes) Fully supported here Open In Colab
Detectron2 here Object detection (bounding boxes) Under beta-testing here Open In Colab
RetinaNet here Object detection (bounding boxes) Under beta-testing here Open In Colab

Image-to-image translation networks

Network Paper(s) Tasks Status Link to example training and test dataset Direct link to the notebook in Colab
Label-free prediction (fnet) 2D here Artificial labelling Under beta-testing Coming soon Open In Colab
Label-free prediction (fnet) 3D here Artificial labelling Fully supported here Open In Colab
CycleGAN here Unpaired Image-to-Image Translation Fully supported here Open In Colab
pix2pix here Paired Image-to-Image Translation Fully supported here Open In Colab

Registration networks

Network Paper(s) Tasks Status Link to example training and test dataset Direct link to the notebook in Colab
DRMIME here Affine or perspective image registration Under beta-testing Coming soon! Open In Colab

BioImage.io notebooks

Networks that are compatible with BioImage.IO and can be used in ImageJ via deepImageJ.

Network Paper(s) Task Link to example training and test dataset Direct link to the notebook in Colab
StarDist (2D) with DeepImageJ export StarDist: here and here, and DeepImageJ Nuclei segmentation here Open In Colab
Deep-STORM with DeepImageJ export Deep-STORM and DeepImageJ Single Molecule Localization Microscopy (SMLM) image reconstruction from high-density emitter data Training data simulated in the notebook or available from here Open In Colab
U-Net (2D) with DeepImageJ export U-Net and DeepImageJ Segmentation ISBI challenge or here Open In Colab
U-Net (3D) with DeepImageJ export 3D U-Net and DeepImageJ Segmentation EPFL dataset Open In Colab

Tools

Network Paper(s) Task Status Link to example training and test dataset Direct link to the notebook in Colab
Augmentor here Image augmentation Fully supported None Open In Colab
Quality Control here Error mapping and quality metrics estimation Fully supported None Open In Colab

Releated projects hosted elsewhere

Network Paper(s) Aim Link to the project Direct link to the notebook in Colab
DeepBacs here Toolbox to use Deep Learning to analyse microscopy images of bacteria here None
CAFI - DAIN here Content-aware frame interpolation using DAIN here Open In Colab
CAFI - ZoomingSlowMo here Content-aware frame interpolation using ZoomingSlowMo here Open In Colab
DECODE here Single Molecule Localization Microscopy (SMLM) image reconstruction here Open In Colab
EM-stellar here Electron microscopy image segmentation here Open In Colab

Contributors

Developers and testers

Founding

Newcomers

Researchers providing guidance and recommendations

Clone this wiki locally