Tympanic membrane generation with generative adversarial networks Çekişmeli üretici aǧlar ile yapay kulak zari görüntülerinin üretimi


Eseoglu M. F., KARSLIGİL YAVUZ M. E., Kocak I.

29th IEEE Conference on Signal Processing and Communications Applications, SIU 2021, Virtual, Istanbul, Turkey, 9 - 11 June 2021 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/siu53274.2021.9477848
  • City: Virtual, Istanbul
  • Country: Turkey
  • Keywords: generative adversarial networks, medical image processing, data augmentation, Visual Turing test
  • Yıldız Technical University Affiliated: Yes

Abstract

© 2021 IEEE.Obtaining sufficient original data in most studies in the field of medical pattern recognition is a difficult and time consuming process. Different data augmentation methods are used to increase the amount of data to be used to train these systems. In this study, a generative adversarial networks based system that produces artificial images by using the tympanic membrane images taken from otoscope devices for data augmentation has been designed and trained. Artificial images that has been generated by different generative adversarial networks have been evaluated by specialist physicians with a Visual Turing test. Preliminary results show that artificial medical images can be perceived as real with high confidence scores.