Dermoscopy diagnosis of cancerous lesions utilizing dual deep learning algorithms via visual and audio (sonification) outputs: Laboratory and prospective observational studies.

Journal: EBioMedicine
Published Date: Jan 20, 2019

Abstract

BACKGROUND: Early diagnosis of skin cancer lesions by dermoscopy, the gold standard in dermatological imaging, calls for a diagnostic upscale. The aim of the study was to improve the accuracy of dermoscopic skin cancer diagnosis through use of novel deep learning (DL) algorithms. An additional sonification-derived diagnostic layer was added to the visual classification to increase sensitivity.

Authors

  • B N Walker
    Sonification Lab, School of Psychology, School of Interactive Computing, Georgia Institute of Technology (Walker BN), Georgia.
  • J M Rehg
    School of Interactive Computing, Georgia Institute of Technology, Atlanta, Georgia.
  • A Kalra
    Hoplabs, Atlanta, Georgia.
  • R M Winters
    Institute of GT Sonification Lab, Georgia Technology, Atlanta, Georgia.
  • P Drews
    Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, Georgia.
  • J Dascalu
    Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel.
  • E O David
    Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel.
  • A Dascalu
    Department of Physiology and Pharmacology, Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel. Electronic address: dasc@post.tau.ac.il.

Keywords

External Resources

Popular Topics
Recent Journals