Abstract: Divide-And-Conquer Approach Towards Understanding Deep Networks

Deep neural networks have achieved tremendous success in various fields including medical image segmentation. However, they have long been criticized for being a black-box, in that interpretation, understanding and correcting architectures is diffcult as there is no general theory for deep neural network design. Previously, precision learning was proposed to fuse deep architectures and traditional approaches.

Authors and Affiliations

1. Pattern Recognition Lab, Friedrich-Alexander University Erlangen-Nürnberg, Erlangen, Deutschland

   Weilin Fu, Katharina Breininger, Roman Schaffert, Nishant Ravikumar & Andreas Maier

2. Erlangen Graduate School in Advanced Optical Technologies(SAOT), Erlangen, Deutschland

   Andreas Maier

3. International Max Planck Research School for Physics of Light (IMPRS-PL), Erlangen, Deutschland

   Weilin Fu

Corresponding author

Correspondence to Weilin Fu .

Editors and Affiliations

1. Institut für Medizinische Informatik, Charité - Universitätsmedizin Berlin, Berlin, Germany

   Thomas Tolxdorff

2. Peter L. Reichertz Institut für Medizinische Informatik, Technische Universität Braunschweig, Braunschweig, Germany

   Thomas M. Deserno

3. Institut für Medizinische Informatik, Universität zu Lübeck, Lübeck, Germany

   Heinz Handels

4. Lehrstuhl für Mustererkennung, Friedrich-Alexander-Universität, Erlangen, Germany

   Andreas Maier

5. Medical Image Computing, E230, Deutsches Krebsforschungszentrum (DKFZ), Heidelberg, Germany

   Klaus H. Maier-Hein

6. Fakultät für Informatik und Mathematik, Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany

   Christoph Palm

Reprints and permissions

© 2020 Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature

Policies and ethics