June 2023
Volume 64, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2023
Automated classification of ophthalmic image quality
Author Affiliations & Notes
  • Richard E. Daws
    Imperial College London, London, London, United Kingdom
    Novai LTD, Reading, United Kingdom
  • James Owler
    Novai LTD, Reading, United Kingdom
  • Jonathan Young
    Novai LTD, Reading, United Kingdom
  • Jake Kenworthy
    Novai LTD, Reading, United Kingdom
  • Natalie Pankova
    Novai LTD, Reading, United Kingdom
  • M Francesca Cordeiro
    Imperial College London, London, London, United Kingdom
    Novai LTD, Reading, United Kingdom
  • Footnotes
    Commercial Relationships   Richard Daws Novai LTD, Code E (Employment); James Owler Novai LTD, Code E (Employment); Jonathan Young Novai LTD, Code E (Employment); Jake Kenworthy Novai LTD, Code E (Employment); Natalie Pankova Novai LTD, Code E (Employment); M Francesca Cordeiro Novai LTD, Code E (Employment)
  • Footnotes
    Support  UKRI Innovate UK 10028366
Investigative Ophthalmology & Visual Science June 2023, Vol.64, 230. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Richard E. Daws, James Owler, Jonathan Young, Jake Kenworthy, Natalie Pankova, M Francesca Cordeiro; Automated classification of ophthalmic image quality. Invest. Ophthalmol. Vis. Sci. 2023;64(8):230.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Excluding poor quality images is important both for clinicians to reliably assess the current status of the eye and for scientists to make valid inferences regarding biomarkers, group-differences or drug efficacy. However, manually reviewing images is time-consuming and is limited by reviewer biases. Here, we developed a machine learning classifier to provide a scalable and objective approach that can automatically detect poor quality images.

Methods : An in-house database of 823 NIRAF human retinal images were manually graded as “bad” or “good” quality by two observers. For each image, image characteristics were captured using a set of 23 features (Figure 1d). This included no-reference (e.g., signal-to-noise ratio) and pseudo-reference metrics (e.g., mutual information) where the image metrics was compared to random uniform noise. A gradient boosting classifier was trained and tested using random 80-20% splits (500 “weak learners”, 0.01 learning rate). This process was repeated 250 times to build performance distributions to compare the model performance to random chance.

Results : Manual observers rated ~28% (237) of the images as poor quality and ~72% (586) as good quality. The trained model correctly classified image quality at an f1-score performance (Figure 1ai) that was significantly above random chance (paired t-test: t(249)=101.59, p<0.001, d=9.07). On average, the model performance was high (Figure 1aii): f1-score=76% (SD=4.8), accuracy=87% (SD=2.5), precision=83% (SD=6.1), sensitivity=71% (SD=6.5%), specificity=94% (SD=2.3). Examining the model weights (Figure 1d) indicated that measures which capture the image’s information content and difference from random noise are most useful for detecting poor image quality.

Conclusions : We demonstrate that machine learning can accurately classify human NIRAF retinal image quality. This approach could be applied in several contexts including improving quality during the real-time image acquisition or for triaging large numbers of images where distinct processing pipelines could be applied based on image quality.

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

 

Figure 1 – Automated image assessment. ai) Model f1-scores performance is significantly above random chance. aii) Model performance metrics. b) Confusion matrix from the best performing model. c) Examples of correctly labelled images. d) Model weights indicating the importance of each image metric for correct classification.

Figure 1 – Automated image assessment. ai) Model f1-scores performance is significantly above random chance. aii) Model performance metrics. b) Confusion matrix from the best performing model. c) Examples of correctly labelled images. d) Model weights indicating the importance of each image metric for correct classification.

×
×

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.

×