Bioinformatics

ilastik – interactive learning and image segmentation toolkit

ilastik is an interactive image analysis application that uses machine learning to classify, segment, track and count objects in scientific images. Its main attraction is that researchers can train classifiers by marking examples directly in their images, without having to develop machine learning algorithms themselves.

The software is particularly useful in biological microscopy, where large datasets may contain cells, tissues or other structures that need to be identified and measured. Users choose a workflow appropriate to their analysis, load the experimental data and provide annotations that guide the classification process.

Predictions are displayed interactively, allowing users to inspect the results and refine their annotations. This feedback-driven approach helps researchers develop image analysis procedures suited to their particular samples and imaging conditions.

This is free and open source software.

Key Features

  • Pixel Classification workflow for assigning image pixels to user-defined categories using interactive brush annotations.
  • Immediate prediction feedback as training labels are added or modified, helping users refine classification results.
  • Selection of image features based on intensity, edges and texture at different spatial scales.
  • Autocontext workflow that uses predictions from an initial classifier as additional information for a second classification stage.
  • Object Classification workflow for categorising segmented objects using properties such as size, shape and intensity.
  • Carving workflow for interactively extracting individual objects from three-dimensional image volumes.
  • Boundary-based segmentation for separating adjacent structures using image boundary information.
  • Tracking workflows for following biological objects through time-series images, including objects that divide.
  • Density Counting workflow for estimating numbers of closely packed objects that are difficult to segment individually.
  • Support for analysing two-dimensional, three-dimensional and time-series image datasets.
  • Batch processing for applying trained classifiers to additional images without repeating the interactive training process.
  • Cross-platform support – runs on Linux, macOS, and Windows.

Website: github.com/ilastik/ilastik
Support:
Developer: ilastik development team
License: GNU General Public License v2.0 with an exception for independent extensions

ilastik is written in Python. Learn Python with our recommended free books and free tutorials.


Related Software

Biology Tools
EMBOSSThe European Molecular Biology Open Software Suite
NAMDParallel, object-oriented molecular dynamics
GROMACSMolecular dynamics simulator, with building and analysis tools
VMDDisplays, animates, and analyzes large biomolecular systems 3-D graphics
simuPOPForward-time population genetics simulation environment
MUSCLEMUltiple Sequence Comparison by Log-Expectation
SeaViewGraphical user interface for molecular phyologeny
SeqVizDNA, RNA, and protein sequence viewer
TREE-PUZZLEReconstruction of phylogenetic trees by maximum likelihood
TreeView XDisplays and prints phylogenetic trees
CellProfilerImage analysis application for researchers
napariPython-based image viewer
COPASIBiochemical systems simulator
VCellModeling and simulation framework
NEURONBuild and run biophysically detailed models
NESTSimulator for spiking neural network models

Read our verdict in the software roundup.


Best Free and Open Source Software LinuxLinks helps you discover the best free and open source software for Linux. Explore our extensive collection of recommended applications, including alternatives to popular proprietary software.

We also publish software reviews, Linux tutorials, hardware reviews, free programming books and articles covering the wider open source community. Browse our Linux resources to discover more.

Know a useful free and open source Linux application we haven't covered? Suggest a program for inclusion.

Has your software been featured on LinuxLinks? Display one of our Featured on LinuxLinks badges on your website or GitHub README.
Subscribe

Please read our Comment Policy before commenting.

Notify of
guest
0 Comments
Oldest
Newest Most Voted