Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Biomarkers of retinal vein occlusions defined by deep learning in Optical Coherence Tomography Angiography scans.
Author Affiliations & Notes
  • Fabio Daniel Padilla-Pantoja
    Universidad Nacional de Colombia, Bogota, Bogota, Colombia
  • Laura Juliana Gallego-Suárez
    Universidad Nacional de Colombia, Bogota, Bogota, Colombia
  • Bernardo Alfonso Quijano-Nieto
    Universidad Nacional de Colombia, Bogota, Bogota, Colombia
  • Oscar Julián Perdomo-Charry
    Universidad Nacional de Colombia, Bogota, Bogota, Colombia
  • Valentina Zambrano Pérez
    Universidad Nacional de Colombia, Bogota, Bogota, Colombia
  • Footnotes
    Commercial Relationships   Fabio Daniel Padilla-Pantoja None; Laura Juliana Gallego-Suárez None; Bernardo Alfonso Quijano-Nieto None; Oscar Julián Perdomo-Charry None; Valentina Zambrano Pérez None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 2342. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Fabio Daniel Padilla-Pantoja, Laura Juliana Gallego-Suárez, Bernardo Alfonso Quijano-Nieto, Oscar Julián Perdomo-Charry, Valentina Zambrano Pérez; Biomarkers of retinal vein occlusions defined by deep learning in Optical Coherence Tomography Angiography scans.. Invest. Ophthalmol. Vis. Sci. 2024;65(7):2342.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop a computational method based on Deep Learning (DL) to automatically detect biomarkers of retinal vein occlusions in images acquired by optical coherence tomography angiography (OCT- A) using retrospective data.

Methods : Images of the superficial, deep, en face, choriocapillaris and outer retina to choriocapillaris (ORCC) layers obtained from 254 patients attended in an Ophthalmology Clinic were used to train and test an artificial intelligence (AI) model. The OCT-A scans were manually annotated with four biomarkers (BMs): disruption of the perifoveal capillary plexus, non-perfusion areas (NPAs), vascular tortuosity and cystoid spaces. Segmentation and identification were subsequently provided to build and training the DL model using Deep Convolutional Neural Networks (DNN). Detection rate and Jaccard index were the main outcome measures.

Results : The detection rate of the model for disruption of the perifoveal capillary plexus, non-perfusion areas, vascular tortuosity and cystoid spaces were 93%, 92%, 91% and 84% respectively. The Jaccard index values were 0.85, 0.77, 0.72 and 0.73 respectively.

Conclusions : The proposed DL model may identify with good performance four key biomarkers of retinal vein occlusions in OCT-A images.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Examples of segmentation of the four key biomarkers: (A) Perifoveal capillary plexus alteration, (B) Cystoid spaces, (C) Areas of non-perfusion, and (D) Vascular tortuosity. From left to right: original optical coherence tomography angiography scan, biomarker segmentation performed by expert ophthalmologists, and model prediction.

Examples of segmentation of the four key biomarkers: (A) Perifoveal capillary plexus alteration, (B) Cystoid spaces, (C) Areas of non-perfusion, and (D) Vascular tortuosity. From left to right: original optical coherence tomography angiography scan, biomarker segmentation performed by expert ophthalmologists, and model prediction.

 

Box-and-whisker plot of the Jaccard index for each biomarker.

Box-and-whisker plot of the Jaccard index for each biomarker.

×
×

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.

×