Automated

​The Allen Cell Structure Segmenter is a Python-based open source toolkit developed at the Allen Institute for Cell Science for 3D segmentation of intracellular structures in fluorescence microscope images.

It consists of two complementary elements:

1. Classic image segmentation workflows for 20 distinct intracellular structure localization patterns. A visual “lookup table” is outlining the modular algorithmic steps for each segmentation workflow. This provides an intuitive guide for selection or construction of new segmentation workflows for a user’s particular segmentation task. 
2. Human-in-the-loop iterative deep learning segmentation workflow trained on ground truth manually curated data from the images segmented with the segmentation workflow. Importantly, this module was not released yet.

DeconvolutionLab2 includes a friendly user interface to run the following deconvolution algortihms: Regularized Inverse Filter, Tikhonov Inverse Filter, Naive Inverse Filter, Richardson-Lucy, Richardson-Lucy Total Variation, Landweber (Linear Least Squares), Non-negative Least Squares, Bounded-Variable Least Squares, Van Cittert, Tikhonov-Miller, Iterative Constraint Tikhonov-Miller, FISTA, ISTA.

The backbone of our software architecture is a library that contains the number-crunching elements of the deconvolution task. It includes the tool for a complete validation pipeline. Inquisitive minds inclined to peruse the code will find it fosters the understanding of deconvolution.

Quote " finding and/or analyzing colocalization of bright intensity spots (cells, particles, vesicles, comets, dots, etc) in images with heterogeneous background (microscopy, astronomy, engineering, etc). "

Uses Gaussian-Mexican hat convolution for preprocessing.

h-Dome transformation, useful for spot detection.

Jython code example:

from de.unihalle.informatik.MiToBo.core.datatypes.images import MTBImage
from de.unihalle.informatik.MiToBo.morphology import HDomeTransform3D
from ij import IJ

imp = IJ.getImage()
mtb = MTBImage.createMTBImage( imp.duplicate() )
hdome = HDomeTransform3D(mtb, 10.0)
hdome.runOp()
mtbdone = hdome.getResultImage()
imp2 = mtbdone.getImagePlus()
imp2.show()

Nessys: Nuclear Envelope Segmentation System

Nessys is a software written in Java for the automated identification of cell nuclei in biological images (3D + time). It is designed to perform well in complex samples, i.e when cells are particularly crowded and heterogeneous such as in embryos or in 3D cell cultures. Nessys is also fast and will work on large images which do not fit in memory.

Nessys also offers an interactive user interface for the curation and validation of segmentation results. Think of this as a 3D painter / editor. This editor can also be used to generate manually segmented images to use as ground truth for testing the accuracy of the automated segmentation method.

Finally Nessys, contains a utility for assessing the accuracy of the automated segmentation method. It works by comparing the result of the automated method to a manually generated ground truth. This utility will provide two types of output: a table with a number of metrics about the accuracy and an image representing a map of the mismatch between the result of the automated method and the ground truth.