Unravelling the effect of data augmentation transformations in polyp segmentation.

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

Abstract

PURPOSE: Data augmentation is a common technique to overcome the lack of large annotated databases, a usual situation when applying deep learning to medical imaging problems. Nevertheless, there is no consensus on which transformations to apply for a particular field. This work aims at identifying the effect of different transformations on polyp segmentation using deep learning.

Authors

  • Luisa F Sánchez-Peralta
    Jesús Usón Minimally Invasive Surgery Centre, Ctra. N-521, km 41.8, 10071 Cáceres, Spain. Electronic address: lfsanchez@ccmijesususon.com.
  • Artzai Picon
    Computer Vision Group, Tecnalia Research & Innovation, Derio, Spain.
  • Francisco M Sánchez-Margallo
    Jesús Usón Minimally Invasive Surgery Centre, Ctra. N-521, km 41.8, 10071 Cáceres, Spain. Electronic address: msanchez@ccmijesususon.com.
  • J Blas Pagador
    Jesús Usón Minimally Invasive Surgery Centre, Ctra. N-521, km 41.8, 10071 Cáceres, Spain. Electronic address: jbpagador@ccmijesususon.com.