ilastik: interactive machine learning for (bio) image analysis

被引：1955

作者：

Berg, Stuart ^{[1
]}

Kutra, Dominik ^{[2
,3
]}

Kroeger, Thorben ^{[2
]}

Straehle, Christoph N. ^{[2
]}

Kausler, Bernhard X. ^{[2
]}

Haubold, Carsten ^{[2
]}

Schiegg, Martin ^{[2
]}

Ales, Janez ^{[2
]}

Beier, Thorsten ^{[2
]}

Rudy, Markus ^{[2
]}

Eren, Kemal ^{[2
]}

Cervantes, Jaime I. ^{[2
]}

Xu, Buote ^{[2
]}

Beuttenmueller, Fynn ^{[2
,3
]}

Wolny, Adrian ^{[2
]}

Zhang, Chong ^{[2
]}

Koethe, Ullrich ^{[2
]}

Hamprecht, Fred A. ^{[2
]}

Kreshuk, Anna ^{[2
,3
]}

机构：

[1] HHMI Janelia Res Campus, Ashburn, VA USA

[2] Heidelberg Univ, HCI IWR, Heidelberg, Germany

[3] European Mol Biol Lab, Heidelberg, Germany

来源：

NATURE METHODS | 2019年 / 16卷 / 12期

关键词：

SEGMENTATION; TOOL;

D O I：

10.1038/s41592-019-0582-9

中图分类号：

Q5 [生物化学];

学科分类号：

070307 [化学生物学];

摘要：

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 non-linear 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.

引用

页码：1226 / 1232

页数：7

共 40 条

[1]

Andres B, 2011, IEEE I CONF COMP VIS, P2611, DOI 10.1109/ICCV.2011.6126550

[2]

Trainable Weka Segmentation: a machine learning tool for microscopy pixel classification [J].