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

Journal: Nature methods
Published Date:

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.

Authors

  • Thorsten Falk
    Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany.
  • Dominic Mai
    Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany.
  • Robert Bensch
    Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany.
  • Özgün Çiçek
    Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany.
  • Ahmed Abdulkadir
    Laboratory for Research in Neuroimaging, Department of Clinical Neurosciences, Lausanne University Hospital (CHUV) and University of Lausanne, Lausanne, Switzerland.
  • Yassine Marrakchi
    Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany.
  • Anton Böhm
    Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany.
  • Jan Deubner
    Optophysiology Lab, Institute of Biology III, Albert-Ludwigs-University, Freiburg, Germany.
  • Zoe Jäckel
    Optophysiology Lab, Institute of Biology III, Albert-Ludwigs-University, Freiburg, Germany.
  • Katharina Seiwald
    Optophysiology Lab, Institute of Biology III, Albert-Ludwigs-University, Freiburg, Germany.
  • Alexander Dovzhenko
    Institute of Biology II, Albert-Ludwigs-University, Freiburg, Germany.
  • Olaf Tietz
    Institute of Biology II, Albert-Ludwigs-University, Freiburg, Germany.
  • Cristina Dal Bosco
    Institute of Biology II, Albert-Ludwigs-University, Freiburg, Germany.
  • Seán Walsh
    Department of Radiation Oncology (MAASTRO Clinic), Dr. Tanslaan 12, Maastricht, The Netherlands.
  • Deniz Saltukoglu
    BIOSS Centre for Biological Signalling Studies, Freiburg, Germany.
  • Tuan Leng Tay
    BrainLinks-BrainTools, Albert-Ludwigs-University, Freiburg, Germany.
  • Marco Prinz
    BIOSS Centre for Biological Signalling Studies, Freiburg, Germany.
  • Klaus Palme
    BIOSS Centre for Biological Signalling Studies, Freiburg, Germany.
  • Matias Simons
    BIOSS Centre for Biological Signalling Studies, Freiburg, Germany.
  • Ilka Diester
    Optophysiology Lab, Institute of Biology III, Albert-Ludwigs-University, Freiburg, Germany.
  • Thomas Brox
  • Olaf Ronneberger
    DeepMind, London, EC4A 3TW, UK.