A dataset of laryngeal endoscopic images with comparative study on convolution neural network-based semantic segmentation.

Journal: International journal of computer assisted radiology and surgery
Published Date:

Abstract

PURPOSE: Automated segmentation of anatomical structures in medical image analysis is a prerequisite for autonomous diagnosis as well as various computer- and robot-aided interventions. Recent methods based on deep convolutional neural networks (CNN) have outperformed former heuristic methods. However, those methods were primarily evaluated on rigid, real-world environments. In this study, existing segmentation methods were evaluated for their use on a new dataset of transoral endoscopic exploration.

Authors

  • Max-Heinrich Laves
    Leibniz Universität Hannover, Appelstraße 11A, 30167, Hannover, Germany. laves@imes.uni-hannover.de.
  • Jens Bicker
    Leibniz Universität Hannover, Appelstraße 11A, 30167, Hannover, Germany.
  • Lüder A Kahrs
    Institute of Mechatronic Systems, Leibniz Universität Hannover, Appelstrasse 11 a, 30167, Hannover, Germany.
  • Tobias Ortmaier
    Institute of Mechatronic Systems, Leibniz Universität Hannover, 30167 Hanover, Germany.