TY  - JOUR
VL  - 2019
EP  - 9
ID  - heidok28283
CY  - London, New York
JF  - Nature Methods
A1  - Berg, Stuart
A1  - Kutra, Dominik
A1  - Kroeger, Thorben
A1  - Straehle, Christoph N.
A1  - Kausler, Bernhard X.
A1  - Haubold, Carsten
A1  - Schiegg, Martin
A1  - Ales, Janez
A1  - Beier, Thorsten
A1  - Rudy, Markus
A1  - Eren, Kemal
A1  - Cervantes, Jaime I
A1  - Xu, Buote
A1  - Beuttenmueller, Fynn
A1  - Wolny, Adrian
A1  - Zhang, Chong
A1  - Koethe, Ullrich
A1  - Hamprecht, Fred A.
A1  - Kreshuk, Anna
AV  - public
IS  - 16
PB  - Nature Publishing Group
SN  - 1548-7105 (Online-Ausg.), 1548-7091 (Druck-Ausg.)
N2  - 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.
SP  - 1
Y1  - 2019/09//
UR  - https://archiv.ub.uni-heidelberg.de/volltextserver/28283/
KW  - deep learning in microscopy
KW  -  machine learning
KW  -  image analysis
TI  - ilastik: interactive machine learning for (bio)image analysis
ER  -