Segmenting skin ulcers and measuring the wound area using deep convolutional networks.

Journal: Computer methods and programs in biomedicine
Published Date:

Abstract

BACKGROUND AND OBJECTIVES: Bedridden patients presenting chronic skin ulcers often need to be examined at home. Healthcare professionals follow the evolution of the patients' condition by regularly taking pictures of the wounds, as different aspects of the wound can indicate the healing stages of the ulcer, including depth, location, and size. The manual measurement of the wounds' size is often inaccurate, time-consuming, and can also cause discomfort to the patient. In this work, we propose the Automatic Skin Ulcer Region Assessment ASURA framework to accurately segment the wound and automatically measure its size.

Authors

  • Daniel Y T Chino
    Institute of Mathematical and Computer Sciences, University of Sao Paulo, Brazil. Electronic address: chinodyt@icmc.usp.br.
  • Lucas C Scabora
    Institute of Mathematical and Computer Sciences, University of Sao Paulo, Brazil. Electronic address: lucascsb@usp.br.
  • Mirela T Cazzolato
    Institute of Mathematical and Computer Sciences, University of Sao Paulo, Brazil. Electronic address: mirelac@usp.br.
  • Ana E S Jorge
    Department of Physical Therapy, DFisio/UFSCar, Brazil.
  • Caetano Traina-Jr
    Institute of Mathematical and Computer Sciences, University of Sao Paulo, Brazil. Electronic address: caetano@icmc.usp.br.
  • Agma J M Traina
    Institute of Mathematics and Computer Sciences, ICMC/USP, Brazil. Electronic address: agma@icmc.usp.br.