Evolutionary image simplification for lung nodule classification with convolutional neural networks.

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

Abstract

PURPOSE: Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions.

Authors

  • Daniel Lückehe
    Computational Health Informatics, Leibniz University Hanover, Schloßwender Str. 5, 30159, Hanover, Germany. lueckehe@chi.uni-hannover.de.
  • Gabriele von Voigt
    Computational Health Informatics, Leibniz University Hanover, Schloßwender Str. 5, 30159, Hanover, Germany.