Deep learning nuclei detection: A simple approach can deliver state-of-the-art results.

Journal: Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
Published Date:

Abstract

BACKGROUND: Deep convolutional neural networks have become a widespread tool for the detection of nuclei in histopathology images. Many implementations share a basic approach that includes generation of an intermediate map indicating the presence of a nucleus center, which we refer to as PMap. Nevertheless, these implementations often still differ in several parameters, resulting in different detection qualities.

Authors

  • Henning Höfener
    Fraunhofer MEVIS, Am Fallturm 1, 28359, Bremen, Germany. Electronic address: henning.hoefener@mevis.fraunhofer.de.
  • André Homeyer
    Fraunhofer MEVIS, Am Fallturm 1, 28359, Bremen, Germany. Electronic address: andre.homeyer@mevis.fraunhofer.de.
  • Nick Weiss
    Fraunhofer MEVIS, Am Fallturm 1, 28359, Bremen, Germany. Electronic address: nick.weiss@mevis.fraunhofer.de.
  • Jesper Molin
    Sectra AB, Teknikringen 20, 58330, Linköping, Sweden. Electronic address: Jesper.Molin@sectra.com.
  • Claes F Lundström
    Sectra AB, Teknikringen 20, 58330, Linköping, Sweden; Center for Medical Image Science and Visualization, Linköping University, 58183, Linköping, Sweden. Electronic address: claes.lundstrom@liu.se.
  • Horst K Hahn
    Fraunhofer MEVIS, Am Fallturm 1, 28359, Bremen, Germany; Jacobs University, Campus Ring 1, 28759, Bremen, Germany. Electronic address: horst.hahn@mevis.fraunhofer.de.