June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Grayscale Retinal Vessel Maps Are Associated with Self-Reported Race: Implications for Artificial Intelligence Models
Author Affiliations & Notes
  • Aaron S Coyner
    Oregon Health & Science University, Portland, Oregon, United States
  • Praveer Singh
    Massachusetts General Hospital, Boston, Massachusetts, United States
  • James Brown
    University of Lincoln, Lincoln, Lincolnshire, United Kingdom
  • Susan Ostmo
    Oregon Health & Science University, Portland, Oregon, United States
  • Robison Vernon Paul Chan
    Illinois Eye and Ear Infirmary, Chicago, Illinois, United States
  • Michael F Chiang
    National Eye Institute, Bethesda, Maryland, United States
  • Jayashree Kalpathy-Cramer
    Massachusetts General Hospital, Boston, Massachusetts, United States
  • J. Peter Campbell
    Oregon Health & Science University, Portland, Oregon, United States
  • Footnotes
    Commercial Relationships   Aaron Coyner None; Praveer Singh None; James Brown Boston AI Lab, Code R (Recipient); Susan Ostmo None; Robison Chan Phoenix Technology Group, Code C (Consultant/Contractor), Genentech, Code F (Financial Support), Siloam, Code O (Owner), Boston AI Lab, Code R (Recipient); Michael Chiang None; Jayashree Kalpathy-Cramer Genentech, Code F (Financial Support), Boston AI Lab, Code R (Recipient); J. Peter Campbell Boston AI Lab, Code C (Consultant/Contractor), Genentech, Code F (Financial Support), Siloam, Code O (Owner), Boston AI Lab, Code R (Recipient)
  • Footnotes
    Support  This work was supported by grants R01 EY19474, R01 EY031331, R21 EY031883, and P30 EY10572 from the National Institutes of Health (Bethesda, MD), and by unrestricted departmental funding and a Career Development Award (JPC) from Research to Prevent Blindness (New York, NY).
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 1155. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Aaron S Coyner, Praveer Singh, James Brown, Susan Ostmo, Robison Vernon Paul Chan, Michael F Chiang, Jayashree Kalpathy-Cramer, J. Peter Campbell; Grayscale Retinal Vessel Maps Are Associated with Self-Reported Race: Implications for Artificial Intelligence Models. Invest. Ophthalmol. Vis. Sci. 2022;63(7):1155.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Artificial intelligence (AI) algorithms can learn and perpetuate racial biases from patterns in medical images if those images contain information relevant to self reported race or ethnicity. Recent studies have shown that convolutional neural networks (CNNs) can be trained to classify images as being from black or white patients from medical images that were not previously thought to contain information relevant to the classification of self-reported race. Herein, we evaluate whether grayscale retinal vessel maps (RVMs) of patients screened for retinopathy of prematurity (ROP) similarly contain the potential for racial bias.

Methods : 4095 retinal fundus images (RFIs) were collected from 245 Black and White infants (as labeled by self-report from parents). A U-Net generated RVMs from RFIs, which were subsequently thresholded, binarized, or skeletonized (Figure). CNNs were then trained to predict self-reported race from color RFIs, raw RVMs, and thresholded, binarized, or skeletonized RVMs. Area under the precision-recall curve (AUC-PR) was evaluated.

Results : CNNs predicted self-reported race from RFIs near perfectly (image-level AUC-PR: 0.999, subject-level AUC-PR: 1.000). Raw RVMs were almost as informative as color RFIs (image-level AUC-PR: 0.938, subject-level AUC-PR: 0.995). Ultimately, CNNs were able to detect whether RFIs or RVMs were from self-reported Black or White babies, regardless of whether images contained color, vessel segmentation brightness differences were nullified, or vessel segmentation widths were normalized.

Conclusions : Both Color RFIs and black and white RVMs contain information relevant to the race of patients. These results suggest that biomarker-based strategies to remove information relevant to race or ethnicity (such as skin or fundus pigmentation) may not be effective, and that the potential for racial bias exists even in images that do not appear to contain relevant information.

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

 

Example RVM transformations. RVMs of self-reported Black and White babies were transformed via thresholding (top row; left, middle, and right panels) and, subsequently, binarizing (middle row) or skeletonizing (bottom row).

Example RVM transformations. RVMs of self-reported Black and White babies were transformed via thresholding (top row; left, middle, and right panels) and, subsequently, binarizing (middle row) or skeletonizing (bottom row).

×
×

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.

×