Synthesizing retinal and neuronal images with generative adversarial nets

Med Image Anal. 2018 Oct:49:14-26. doi: 10.1016/j.media.2018.07.001. Epub 2018 Jul 4.

Abstract

This paper aims at synthesizing multiple realistic-looking retinal (or neuronal) images from an unseen tubular structured annotation that contains the binary vessel (or neuronal) morphology. The generated phantoms are expected to preserve the same tubular structure, and resemble the visual appearance of the training images. Inspired by the recent progresses in generative adversarial nets (GANs) as well as image style transfer, our approach enjoys several advantages. It works well with a small training set with as few as 10 training examples, which is a common scenario in medical image analysis. Besides, it is capable of synthesizing diverse images from the same tubular structured annotation. Extensive experimental evaluations on various retinal fundus and neuronal imaging applications demonstrate the merits of the proposed approach.

Keywords: Data-driven image synthesis; Deep learning; Neuronal image synthesis; Retinal fundus image synthesis.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Diagnostic Techniques, Ophthalmological
  • Humans
  • Image Processing, Computer-Assisted / methods*
  • Neural Networks, Computer*
  • Phantoms, Imaging
  • Retinal Neurons*
  • Retinal Vessels / diagnostic imaging*