Domain-specific classification-pretrained fully convolutional network encoders for skin lesion segmentation.

Journal: Computers in biology and medicine
Published Date:

Abstract

BACKGROUND AND OBJECTIVE: Fully convolutional neural networks have been shown to perform well for automated skin lesion segmentation on digital dermatoscopic images. Our concept is that transferring encoder weights from a network trained on a classification task on images of the same domain may contain useful information for segmentation.

Authors

  • Philipp Tschandl
    Department of Computing Science, Simon Fraser University, Burnaby, British Columbia, Canada.
  • Christoph Sinz
    ViDIR Group, Department of Dermatology, Medical University of Vienna, Vienna, Austria. Electronic address: christoph.sinz@meduniwien.at.at.
  • Harald Kittler
    ViDIR Group, Department of Dermatology, Medical University of Vienna, Vienna, Austria. Electronic address: harald.kittler@meduniwien.at.at.