Electron microscopy

CellStich proposes a set of tools for 3D segmentation from 2D segmentation: it reassembles 2D labels obtained from cell in slices in unique 3D labels across slices. It isparticularly robust to anisotropy, and is the ideal companion to cellpose 2D models or other 2D deep learning based models. One could also think about using it for cell tracking by overlap (using time as a third dimension).

ZeroCostDL4Mic: exploiting Google Colab to develop a free and open-source toolbox for Deep-Learning in microscopy

ZeroCostDL4Mic is a collection of self-explanatory Jupyter Notebooks for Google Colab that features an easy-to-use graphical user interface. They are meant to quickly get you started on learning to use deep-learning for microscopy. 

BiaPy is an open source Python library for building bioimage analysis pipelines. 

BiaPy contains ready-to-use solutions for the tasks of semantic segmentation, instance segmentation, object detection, image denoising, single image super-resolution, self-supervised learning and image classification. 

Relate is a correlative software package optimised to work with EM, EDS, EBSD, & AFM data and images.  It provides the tools you need to correlate data from different microscopes, visualise multi-layered data in 2D and 3D, and conduct correlative analyses.

• Combining data from different imaging modalities (e.g. AFM, EDS & EBSD)

• Interactive display of multi-layer correlated data

• Analytical tools for metadata interrogation

• Documented workflows and processes

Correlate

• Import data from AZtec using the H5oina file format
• Import AFM data
• Correlate both sets of data using intuitive image overlays and image matching tools
• Produce combined multimodal datasets

Visualise

• 2D display of multi-layered data
• 3D visualisation of topography combined with AFM material properties, EM images, and EDS & EBSD map overlays
• Customisation of colour palettes, data overlays, image rendering options, and document display
• Export images and animations

Analyse

• Generate profile (cross section) views of multimodal data
• Measure and quantify data across multiple layers
• Analyse areas via data thresholding using amount of x-ray counts, phase maps, height, or other material properties.
• Select an extensive range of measurement parameters
• Export analytical data to text or CSV files

The empanada-napari plugin is built to democratize deep learning image segmentation for researchers in electron microscopy (EM). It ships with MitoNet, a generalist model for the instance segmentation of mitochondria. There are also tools to quickly build and annotate training datasets, train generic panoptic segmentation models, finetune existing models, and scalably run inference on 2D or 3D data. To make segmentation model training faster and more robust, CEM pre-trained weights are used by default. These weights were trained using an unsupervised learning algorithm on over 1.5 million EM images from hundreds of unique EM datasets making them remarkably general.