Skin Lesion Classification Using CNNs With Patch-Based Attention and Diagnosis-Guided Loss Weighting.

Journal: IEEE transactions on bio-medical engineering
Published Date:

Abstract

OBJECTIVE: This paper addresses two key problems of skin lesion classification. The first problem is the effective use of high-resolution images with pretrained standard architectures for image classification. The second problem is the high-class imbalance encountered in real-world multi-class datasets.

Authors

  • Nils Gessert
    Hamburg University of Technology, Schwarzenbergstraße 95 21073, Hamburg. Electronic address: mfbeg@sfu.ca.
  • Thilo Sentker
  • Frederic Madesta
  • Rudiger Schmitz
  • Helge Kniep
  • Ivo Baltruschat
  • Rene Werner
  • Alexander Schlaefer
    Institute of Medical Technology, Hamburg University of Technology, Hamburg, Germany. schlaefer@tuhh.de.