| Literature DB >> 30559429 |
Thorsten Falk1,2,3, Dominic Mai1,2,4,5, Robert Bensch1,2,6, Özgün Çiçek1, Ahmed Abdulkadir1,7, Yassine Marrakchi1,2,3, Anton Böhm1, Jan Deubner8,9, Zoe Jäckel8,9, Katharina Seiwald8, Alexander Dovzhenko10,11, Olaf Tietz10,11, Cristina Dal Bosco10, Sean Walsh10,11, Deniz Saltukoglu2,12,13,14, Tuan Leng Tay9,15,16, Marco Prinz2,3,15, Klaus Palme2,10, Matias Simons2,12,13,17, Ilka Diester8,9,18, Thomas Brox1,2,3,9, Olaf Ronneberger19,20,21.
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.Entities:
Mesh：
Year: 2018 PMID： 30559429 DOI： 10.1038/s41592-018-0261-2
Source DB: PubMed Journal: Nat Methods ISSN： 1548-7091 Impact factor: 28.547