June 2023
Volume 64, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2023
RETIMAT: an open-source software for retinal OCT image analysis
Author Affiliations & Notes
  • David Romero-Bascones
    Biomedical Engineering Department, Mondragon Unibertsitatea, Mondragón, Spain
    Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom
  • Ane Murueta-Goyena
    Neurodegenerative Diseases Group, Biocruces Bizkaia Health Research Institute, Barakaldo, Spain
    Department of Neuroscience, University of the Basque Country, Leioa, Spain
  • Siegfried Wagner
    University College London Institute of Ophthalmology, London, United Kingdom
    Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom
  • Robbert Struyven
    University College London Centre for Medical Image Computing, London, United Kingdom
    Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom
  • Dominic Williamson
    University College London Institute of Ophthalmology, London, United Kingdom
    Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom
  • Pearse Keane
    University College London Institute of Ophthalmology, London, United Kingdom
    Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom
  • Miatane Barrenechea
    Biomedical Engineering Department, Mondragon Unibertsitatea, Mondragón, Spain
  • Iñigo Gabilondo
    Neurodegenerative Diseases Group, Biocruces Bizkaia Health Research Institute, Barakaldo, Spain
    IKERBASQUE, The Basque Foundation for Science, Bilbao, Spain
  • Unai Ayala
    Biomedical Engineering Department, Mondragon Unibertsitatea, Mondragón, Spain
  • Footnotes
    Commercial Relationships   David Romero-Bascones None; Ane Murueta-Goyena None; Siegfried Wagner None; Robbert Struyven None; Dominic Williamson None; Pearse Keane Apellis, Code C (Consultant/Contractor), Allergan, Topcon, Heidelberg Engineering, Novartis, Roche, Bayer, Code F (Financial Support), Big Picture Medical, Code I (Personal Financial Interest); Miatane Barrenechea None; Iñigo Gabilondo None; Unai Ayala None
  • Footnotes
    Support  This work was partially co-funded by the Instituto de Salud Carlos III through the projects “PI14/00679” and “PI16/00005”, by the Basque Foundation for Health Innovation and Research (BIOEF) through the project "BIO17 / ND / 010" and by the Department of Health of the Basque Government through the projects “2019111100”, “2020333033”.
Investigative Ophthalmology & Visual Science June 2023, Vol.64, 2923. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      David Romero-Bascones, Ane Murueta-Goyena, Siegfried Wagner, Robbert Struyven, Dominic Williamson, Pearse Keane, Miatane Barrenechea, Iñigo Gabilondo, Unai Ayala; RETIMAT: an open-source software for retinal OCT image analysis. Invest. Ophthalmol. Vis. Sci. 2023;64(8):2923.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Open-source software plays a major role in medical image analysis: it reduces the time from concept to analysis and enhances reproducibility. Despite its importance, there are very few libraries devoted to optical coherence tomography (OCT) image analysis. To address this need we present RETIMAT, an open-source library for retinal OCT image visualization and feature extraction.

Methods : The software has been developed in MATLAB as an easy-to-use application programming interface composed of independent functions that fulfill specific tasks in the OCT analysis pipeline. These functions are grouped into modules with similar logic (input/output, visualization, …) so that different custom OCT processing pipelines can be built depending on the use case. A summary of the implemented functions is shown in the Figure.

First, RETIMAT provides a simple interface for proprietary OCT file reading (fda, e2e, vol and img formats). Second, it includes functions to compute image quality metrics (e.g., SNR, CNR) as well as visualization reports to inspect the data before any formal analysis. Finally, the user can compute a comprehensive set of numerical features ranging from conventional sectorized thickness values to more advanced features derived from texture analysis, foveal pit morphology and image reflectance. Importantly, part of the feature extraction and visualization logic has already been translated into Python language with the aim of creating a standalone package.

Results : RETIMAT has already proven to be useful in actual research investigating the relationship between demographical factors and macular morphology. Additionally, it has also been successfully used to build the main OCT feature extraction pipeline in AlzEye, a database with more than 1 million OCT images. In both cases, RETIMAT was used for image quality assessment and feature extraction.

Conclusions : RETIMAT is an open-source software aimed at facilitating the analysis of OCT images. It enables both qualitative and quantitative research via a set of visualization and feature extraction tools that help automate OCT image analysis. The code is available at https://github.com/drombas/retimat.

This abstract was presented at the 2023 ARVO Annual Meeting, held in New Orleans, LA, April 23-27, 2023.

 

Overview of RETIMAT functions

Overview of RETIMAT functions

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×