June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Automated machine learning for diagnosis of geographic atrophy and subfoveal involvement using real-world fundus autofluorescence and infrared reflectance images
Author Affiliations & Notes
  • Zhongdi Chu
    Verana Health, California, United States
  • Michael Mbagwu
    Byers Eye Institute, Stanford University School of Medicine, Stanford, California, United States
    Verana Health, California, United States
  • Durga Borka
    Duke University Department of Ophthalmology, Durham, North Carolina, United States
    Verana Health, California, United States
  • Aishwarya Ramakrishnan
    Verana Health, California, United States
  • Ketki Khapare
    Verana Health, California, United States
  • Carlos Candano
    Verana Health, California, United States
  • Aracelis Z Torres
    Verana Health, California, United States
  • Hylton Kalvaria
    Verana Health, California, United States
  • Matthew T Roe
    Verana Health, California, United States
  • Theodore Leng
    Byers Eye Institute, Stanford University School of Medicine, Stanford, California, United States
    Verana Health, California, United States
  • Footnotes
    Commercial Relationships   Zhongdi Chu Verana Health, Code E (Employment); Michael Mbagwu Verana Health, Code E (Employment); Durga Borka Verana Health, Code C (Consultant/Contractor); Aishwarya Ramakrishnan Verana Health, Code E (Employment); Ketki Khapare Verana Health, Code E (Employment); Carlos Candano Verana Health, Code E (Employment); Aracelis Torres Verana Health, Code E (Employment); Hylton Kalvaria Verana Health, Code E (Employment); Matthew Roe Verana Health, Code E (Employment); Theodore Leng Verana Health, Code C (Consultant/Contractor)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 1034 – F0281. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Zhongdi Chu, Michael Mbagwu, Durga Borka, Aishwarya Ramakrishnan, Ketki Khapare, Carlos Candano, Aracelis Z Torres, Hylton Kalvaria, Matthew T Roe, Theodore Leng; Automated machine learning for diagnosis of geographic atrophy and subfoveal involvement using real-world fundus autofluorescence and infrared reflectance images. Invest. Ophthalmol. Vis. Sci. 2022;63(7):1034 – F0281.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop a machine learning(ML) aided pipeline to automatically confirm geographic atrophy(GA) using real-world fundus autofluorescence(FAF) and infrared reflectance(IR) images linked to the IRIS Registry

Methods : The American Academy of Ophthalmology IRIS® Registry(Intelligent Research in Sight)is the nation’s first comprehensive eye disease clinical database, with over 70% of US ophthalmologists contributing. A ML aided pipeline was developed for the IRIS Registry, using a de-identified clinicoimaging dataset with images contributed by 2 large retina practices, patients with a dry age-related macular degeneration(AMD) diagnosis were identified from 2006 to 2019. ML models were developed to assess FAF and IR image quality using features of signal, contrast, noise and sharpness. FAF images with a predicted quality score lower than 0.4[range: 0-1] were excluded. For patients with multiple images at the same encounters, or multiple encounters, the image with the highest quality score was selected. Lastly, training and testing sets were selected using patient-level stratified sampling(age, sex, and race) and labeled by a trained grader. Two deep learning models were developed to classify patients into three categories: no GA, GA without subfoveal involvement, and GA with subfoveal involvement. The models were trained on the training sets with an 80:20 split for training and validation. The trained models were then deployed on the entire cohort

Results : In total, 15,023 FAF and 16,470 IR images from 4,372 eyes of 2,248 patients were identified. After removing low quality images(1,931 FAF images) and multiple images from the same visit(6,825 FAF images, 8,285 IR images), 6,267 pairs of FAF and IR images from 3,372 eyes of 1,872 patients were included. A training set of 442 patients and a testing set of patients(one pair of FAF and IR images per patient) were selected from the cohort. A modified VGG network was developed for GA diagnosis. The model achieved an accuracy of 0.96, 0.96 and 0.94 for training, validation and testing, respectively. The second model for subfoveal involvement is under development

Conclusions : The proposed pipeline demonstrated satisfactory performance confirming GA in AMD eyes using images collected in routine practice. It could potentially be useful in screening patients for GA trials and future GA treatments

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

×
×

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.

×