Surgical scene generation and adversarial networks for physics-based iOCT synthesis

Michael Sommersperger, Alejandro Martin-Gomez, Kristina Mach, Peter Louis Gehlbach, M. Ali Nasseri, Iulian Iordachita, Nassir Navab

Research output: Contribution to journalArticlepeer-review


The development and integration of intraoperative optical coherence tomography (iOCT) into modern operating rooms has motivated novel procedures directed at improving the outcome of ophthalmic surgeries. Although computer-assisted algorithms could further advance such interventions, the limited availability and accessibility of iOCT systems constrains the generation of dedicated data sets. This paper introduces a novel framework combining a virtual setup and deep learning algorithms to generate synthetic iOCT data in a simulated environment. The virtual setup reproduces the geometry of retinal layers extracted from real data and allows the integration of virtual microsurgical instrument models. Our scene rendering approach extracts information from the environment and considers iOCT typical imaging artifacts to generate cross-sectional label maps, which in turn are used to synthesize iOCT B-scans via a generative adversarial network. In our experiments we investigate the similarity between real and synthetic images, show the relevance of using the generated data for image-guided interventions and demonstrate the potential of 3D iOCT data synthesis.

Original languageEnglish (US)
Pages (from-to)2414-2430
Number of pages17
JournalBiomedical Optics Express
Issue number4
StatePublished - Apr 1 2022

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Biotechnology


Dive into the research topics of 'Surgical scene generation and adversarial networks for physics-based iOCT synthesis'. Together they form a unique fingerprint.

Cite this