ilastik: interactive machine learning for (bio)image analysis
| Autor: | Buote Xu, Thorben Kroeger, Jaime I Cervantes, Ullrich Koethe, Martin Schiegg, Christoph N. Straehle, Markus Rudy, Dominik Kutra, Adrian Wolny, Janez Ales, Fynn Beuttenmueller, Anna Kreshuk, Kemal Eren, Carsten Haubold, Fred A. Hamprecht, Stuart Berg, Chong Zhang, Thorsten Beier, Bernhard X. Kausler |
|---|---|
| Jazyk: | angličtina |
| Předmět: |
Computer science
Image processing Machine learning computer.software_genre Endoplasmic Reticulum Biochemistry 570 Life sciences Image (mathematics) Machine Learning 03 medical and health sciences Image Processing Computer-Assisted Humans Molecular Biology 004 Data processing Computer science 600 Technology (Applied sciences) 030304 developmental biology Cell Proliferation 0303 health sciences End user business.industry Aryl Hydrocarbon Receptor Nuclear Translocator Process (computing) Cell Biology Image segmentation Object (computer science) Workflow Line (geometry) Artificial intelligence Collagen business computer Biotechnology |
| Zdroj: | Nature Methods |
| ISSN: | 1548-7105 1548-7091 |
| DOI: | 10.1038/s41592-019-0582-9 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|