Format

Send to

Choose Destination
Nat Methods. 2019 Jan;16(1):67-70. doi: 10.1038/s41592-018-0261-2. Epub 2018 Dec 17.

U-Net: deep learning for cell counting, detection, and morphometry.

Falk T1,2,3, Mai D1,2,4,5, Bensch R1,2,6, Çiçek Ö1, Abdulkadir A1,7, Marrakchi Y1,2,3, Böhm A1, Deubner J8,9, Jäckel Z8,9, Seiwald K8, Dovzhenko A10,11, Tietz O10,11, Dal Bosco C10, Walsh S10,11, Saltukoglu D2,12,13,14, Tay TL9,15,16, Prinz M2,3,15, Palme K2,10, Simons M2,12,13,17, Diester I8,9,18, Brox T1,2,3,9, Ronneberger O19,20,21.

Author information

1
Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany.
2
BIOSS Centre for Biological Signalling Studies, Freiburg, Germany.
3
CIBSS Centre for Integrative Biological Signalling Studies, Albert-Ludwigs-University, Freiburg, Germany.
4
Life Imaging Center, Center for Biological Systems Analysis, Albert-Ludwigs-University, Freiburg, Germany.
5
SICK AG, Waldkirch, Germany.
6
ANavS GmbH, München, Germany.
7
University Hospital of Old Age Psychiatry and Psychotherapy, University of Bern, Bern, Switzerland.
8
Optophysiology Lab, Institute of Biology III, Albert-Ludwigs-University, Freiburg, Germany.
9
BrainLinks-BrainTools, Albert-Ludwigs-University, Freiburg, Germany.
10
Institute of Biology II, Albert-Ludwigs-University, Freiburg, Germany.
11
ScreenSYS GmbH, Freiburg, Germany.
12
Center for Biological Systems Analysis (ZBSA), Albert-Ludwigs-University, Freiburg, Germany.
13
Renal Division, University Medical Centre, Freiburg, Germany.
14
Spemann Graduate School of Biology and Medicine (SGBM), Albert-Ludwigs-University, Freiburg, Germany.
15
Institute of Neuropathology, University Medical Centre, Freiburg, Germany.
16
Institute of Biology I, Albert-Ludwigs-University, Freiburg, Germany.
17
Paris Descartes University-Sorbonne Paris Cité, Imagine Institute, Paris, France.
18
Bernstein Center Freiburg, Albert-Ludwigs-University, Freiburg, Germany.
19
Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany. ronneber@informatik.uni-freiburg.de.
20
BIOSS Centre for Biological Signalling Studies, Freiburg, Germany. ronneber@informatik.uni-freiburg.de.
21
DeepMind, London, UK. ronneber@informatik.uni-freiburg.de.

Abstract

U-Net is a generic deep-learning solution for frequently occurring quantification tasks such as cell detection and shape measurements in biomedical image data. We present an ImageJ plugin that enables non-machine-learning experts to analyze their data with U-Net on either a local computer or a remote server/cloud service. The plugin comes with pretrained models for single-cell segmentation and allows for U-Net to be adapted to new tasks on the basis of a few annotated samples.

PMID:
30559429
DOI:
10.1038/s41592-018-0261-2
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center