EM-net

This repository is official implementation of EM-net: Deep learning for electron microscopy image segmentation on Google Colab.

Important: For better and ultimate inference results, we recommend the users to switch to the Colab Pro where they can utilise Tesla P100 GPU.

This notebook represents the implementation of the EM-net. In addition to the EM-net, a variety of other deep learning methods have also been implemented including U-net, SegNet, ResNet and VGG. All these networks represent a similar encoding-decoding scheme for image segmentation. We have implemented a variety of evaluation metrics which allows you to obtain the maximum desirable performance. Moreover, this notebook offers K-fold cross valiadtion that can be used for training these networks when the training data is limited. Finally, this notebook will enable the users to use ensemble of desirable models for final stage inference on the test data.

Papers related to this Notebook:

EM-net: Deep learning for electron microscopy image segmentation by Afshin Khadangi, Thomas Boudier, Vijay Rajagopal (https://www.biorxiv.org/content/10.1101/2020.02.03.933127v1)
U-Net: Convolutional Networks for Biomedical Image Segmentation by Olaf Ronneberger, Philipp Fischer, Thomas Brox (https://arxiv.org/abs/1505.04597)
Very Deep Convolutional Networks for Large-Scale Image Recognition by Karen Simonyan, Andrew Zisserman (https://arxiv.org/abs/1409.1556)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation by Vijay Badrinarayanan, Alex Kendall, Roberto Cipolla (https://arxiv.org/abs/1511.00561)
Deep Residual Learning for Image Recognition by Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun (https://arxiv.org/abs/1512.03385)

Please cite this original paper when using or developing this notebook.

This notebook is adapted and developed from the ZeroCostDL4Mic.

How to use?!

We have provided the instructions for the usage of this Notebook in the following YouTube link:

YoutTube Video: Walk through the pipeline including data upload, training and deploying the trained model.

Important: Make sure that you create a copy of the following Colab Notebook on your Google Drive before running or making any changes to the notebook

We have provided the instructions for the usage of this Notebook in the following link:

Colab Notebook: Walk through the pipeline including data upload, training and deploying the trained model.

Structure of a notebook

The notebook contains two types of cell:

Text cells provide information and can be modified by douple-clicking the cell. You are currently reading the text cell. You can create a new text by clicking + Text.

Code cells contain code and the code can be modfied by selecting the cell. To execute the cell, move your cursor on the [ ]-mark on the left side of the cell (play button appears). Click to execute the cell. After execution is done the animation of play button stops. You can create a new coding cell by clicking + Code.

Table of contents, Code snippets and Files

On the top left side of the notebook you find three tabs which contain from top to bottom:

Table of contents = contains structure of the notebook. Click the content to move quickly between sections.

Code snippets = contain examples how to code certain tasks. You can ignore this when using this notebook.

Files = contain all available files. After mounting your google drive (see section 1.) you will find your files and folders here.

Remember that all uploaded files are purged after changing the runtime. All files saved in Google Drive will remain. You do not need to use the Mount Drive-button; your Google Drive is connected in section 1.2.

Note: The "sample data" in "Files" contains default files. Do not upload anything in here!

Making changes to the notebook

You can make a copy of the notebook and save it to your Google Drive. To do this click file -> save a copy in drive.