Contents

We will cover the theory behind some useful image preprocessing operations such as filtering for image restoration and feature enhancements, illumination compensation and background correction. We will then combine these operations and write a complete image analysis macro including image correction and 2D stitching of images coming from a large multiposition experiment.

In this session we will be covering ImageJ macro task automation for the batch processing of multiple images. Different techniques will be introduced, contrasted and illustrated in the context of practical bioimage analysis applications. Since image preprocessing typically involves the mechanical application of a sequence of fixed, predictable operations it is often interesting to automate it with ImageJ macro language.

ImageJ, for those with GUI knowledge but without scripting knowledge

Biologists and microscope experts acquire image data. Computational scientists design and implement image processing and analysis algorithms Bioimage analysis is a way of integrating these two resources and to come up with numerical interpretations of biological systems. As this is a still rapidly developing field, standardized procedure is poorly established and we have much more room to develop. Even then, we do have some general approaches that we should take.

The Image Data Explorer is a Shiny app that allows the interactive visualization of images and ROIs associated with data points shown in a scatter plot. It is useful for exploring the relationships between images/ROIs and associated data represented in tabular format. Additional functionalities include data annotation, dimensionality reduction and classification and feature selection.

On the home page the links in the Category panel (Training materials/Dataset/Software) all points to the advanced search page. 

I dont think this is expected, the panel below works fine though.

Video and detailed protocol for setting up a multi-view, multi-channel,  time-lapse light-sheet imaging experiment using zebrafish embryos. As well as the necessary image processing for registration and fusion / deconvolution of the generated image data. 

A command line tool that allows to quantitatively compare two volumes of binary segmentations. Implements 22 different metrics for comparing segmentations such as Dice Coefficient, Hausdorff Distance and average Distance. 

A Python based workflow management software that allows to create workflows that seamlessly scale from a single workstation to a high performance computing cluster or cloud environments. 

Automated workflow for performing multiview reconstruction of large multiview, multichannel, multiillumination time-lapse SPIM data on a high performance computing (HPC) cluster or on a single workstation. 

Code to segment yeast cells using a pre-trained mask-rcnn model. We've tested this with yeast cells imaged in fluorescent images and brightfield images, and gotten good results with both modalities. This code implements an user-friendly script that hides all of the messy implementation details and parameters. Simply put all of your images to be segmented into the same directory, and then plug and go.

This python toolbox performs registration between 2-D microscopy images from the same tissue section or serial sections in several ways to achieve imaging mass spectrometry (IMS) experimental goals.

This code supports the following works and enables others to perform the workflows outlined in the following works, please cite them if you use this toolbox:

NEUBIAS-WG5 workflow for nuclei segmentation using ilastik v1.3.2 and Python post-processing.

This is an implementation of Mask R-CNN on Python 3, Keras, and TensorFlow. The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a ResNet101 backbone.

NEUBIAS-WG5 workflow for nuclei segmentation using Mask-RCNN. The workflow uses Matterport Mask-RCNN. Keras implementation. The model was trained with Kaggle 2018 Data Science Bowl images.

This workflow predict landmark positions on images by using DMBL landmark detection models.

An implementation of Belief Propagation for factor graphs, also known as the sum-product algorithm

This workflow trains DMBL landmark detection models from a dataset of annotated images.

This workflow predict landmark positions on images by using LC landmark detection models.

This workflow trains LC landmark detection models from a dataset of annotated images.