Advertisement

Synthetic Fundus Fluorescein Angiography using Deep Neural Networks

  • Florian Schiffers
  • Zekuan Yu
  • Steve Arguin
  • Andreas Maier
  • Qiushi Ren
Conference paper
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

Fundus fluorescein angiography yields complementary image information when compared to conventional fundus imaging. Angiographic imaging, however, may pose risks of harm to the patient. The output from both types of imaging have different characteristics, but the most prominent features of the fundus are shared in both images. Thus, the question arises if conventional fundus images alone provide enough information to synthesize an angiographic image. Our research analyzes the capacity of deep neural networks to synthesize virtual angiographic images from their conventional fundus counterparts.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. 1.
    Abràmoff MD, Garvin MK, Sonka M. Retinal imaging and image analysis. IEEE Rev Biomed Eng. 2010;3:169–208.Google Scholar
  2. 2.
    Shoughy SS, Kozak I. Selective and complementary use of Optical Coherence Tomography and Fluorescein Angiography in retinal practice. Eye and Vision. 2016;3(1):26.Google Scholar
  3. 3.
    Musa F, Muen W, Hancock R, et al. Adverse effects of fluorescein angiography in hypertensive and elderly patients. Acta Ophthalmologica. 2006;84(6).Google Scholar
  4. 4.
    Nie D, Cao X, Gao Y, et al.; Springer. Estimating CT image from MRI data using 3D fully convolutional networks. International Workshop on Large-Scale Annotation of Biomedical Data and Expert Label Synthesis; p. 170–178.Google Scholar
  5. 5.
    Wolterink JM, Dinkla AM, Savenije MH, et al. Deep MR to CT Synthesis using Unpaired Data. arXiv preprint arXiv:170801155.
  6. 6.
    Costa P, Galdran A, Meyer MI, et al. Towards adversarial retinal image synthesis. arXiv:170108974. 2017.
  7. 7.
    Zhu JY, Park T, Isola P, et al. Unpaired image-to-image translation using cycleconsistent adversarial networks. arXiv preprint arXiv:170310593.
  8. 8.
    Isola P, Zhu JY, Zhou T, et al. Image-to-image translation with conditional adversarial networks. arXiv preprint arXiv:161107004. 2016.
  9. 9.
    Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. Adv neural Inform Process Systems; p. 2672–2680.Google Scholar
  10. 10.
    Hajeb Mohammad Alipour S, Rabbani H, Akhlaghi MR. Diabetic retinopathy grading by digital curvelet transform. Comput Math method Med. 2012;2012.Google Scholar

Copyright information

© Springer-Verlag GmbH Deutschland 2018

Authors and Affiliations

  • Florian Schiffers
    • 1
    • 2
  • Zekuan Yu
    • 1
  • Steve Arguin
    • 1
  • Andreas Maier
    • 2
  • Qiushi Ren
    • 1
  1. 1.Department of Biomedical EngineeringPeking UniversityBeijing ShiChina
  2. 2.Pattern Recognition LabUniversity of Erlangen-NurembergErlangenDeutschland

Personalised recommendations