| Literature DB >> 31570887 |
Stuart Berg1, Dominik Kutra2,3, Thorben Kroeger2, Christoph N Straehle2, Bernhard X Kausler2, Carsten Haubold2, Martin Schiegg2, Janez Ales2, Thorsten Beier2, Markus Rudy2, Kemal Eren2, Jaime I Cervantes2, Buote Xu2, Fynn Beuttenmueller2,3, Adrian Wolny2, Chong Zhang2, Ullrich Koethe2, Fred A Hamprecht4, Anna Kreshuk5,6.
Abstract
We present ilastik, an easy-to-use interactive tool that brings machine-learning-based (bio)image analysis to end users without substantial computational expertise. It contains pre-defined workflows for image segmentation, object classification, counting and tracking. Users adapt the workflows to the problem at hand by interactively providing sparse training annotations for a nonlinear classifier. ilastik can process data in up to five dimensions (3D, time and number of channels). Its computational back end runs operations on-demand wherever possible, allowing for interactive prediction on data larger than RAM. Once the classifiers are trained, ilastik workflows can be applied to new data from the command line without further user interaction. We describe all ilastik workflows in detail, including three case studies and a discussion on the expected performance.Entities:
Mesh：
Substances：
Year: 2019 PMID： 31570887 DOI： 10.1038/s41592-019-0582-9
Source DB: PubMed Journal: Nat Methods ISSN： 1548-7091 Impact factor: 28.547