July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
Estimation of Haemoglobin A1c from Retinal photographs via Deep Learning.
Author Affiliations & Notes
  • Yih Chung Tham
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
  • Yong Liu
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
    Institute of High Performance Computing, A STAR, Singapore
  • Daniel Ting
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
  • Gabriel Ci'en Tjio
    Institute of High Performance Computing, A STAR, Singapore
  • Ayesha Anees
    Institute of High Performance Computing, A STAR, Singapore
  • Gavin Siew Wei Tan
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
  • Charumathi Sabanayagam
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
  • Rick Goh
    Institute of High Performance Computing, A STAR, Singapore
  • Tien Y Wong
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
  • Ching-Yu Cheng
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
  • Footnotes
    Commercial Relationships   Yih Chung Tham, None; Yong Liu, None; Daniel Ting, None; Gabriel Tjio, None; Ayesha Anees, None; Gavin Tan, None; Charumathi Sabanayagam, None; Rick Goh, None; Tien Wong, None; Ching-Yu Cheng, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1456. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Yih Chung Tham, Yong Liu, Daniel Ting, Gabriel Ci'en Tjio, Ayesha Anees, Gavin Siew Wei Tan, Charumathi Sabanayagam, Rick Goh, Tien Y Wong, Ching-Yu Cheng; Estimation of Haemoglobin A1c from Retinal photographs via Deep Learning.. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1456.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Deep learning system (DLS) is a machine learning technology and has gained tremendous traction in medical imaging recently. In the field of ophthalmology, it has also been shown that DLS can extract new knowledge from retinal fundus images. The aim of this study was to evaluate the performance of a newly developed DLS in estimating Haemoglobin A1c (HbA1c), an important marker for diabetes.

Methods : In this study, we retrospectively included 17,422 multi-ethnic Asian individuals from 5 population-based and clinical eye studies in Singapore. Retinal photos and clinical HbA1c measurement from serum sample were collected for all participants. Of the total set, 13,937 individuals’ data (25,637 fundus images) were used for training and development of the DLS; another independent set of 3,485 individuals’ data (6380 fundus images) were used for validation of the DLS. Only macular-centred retinal photos of sufficient quality were selected for DLS training and subsequent validation. Serum HbA1c measurement was used as ‘ground truth’ data in this instance. The mean (standard deviation) of serum HbA1c in training set was 6.31% (1.32), with a wide range of 3.9 to 15.1%. The ResNet and DenseNet convoluted neural networks were used for training of the DLS model. Agreement between DLS-predicted and actual serum HbA1c measurements were evaluated with mean absolute error (MAE), Bland Altman (BA) plots (mean difference and limits of agreement [LOA]), and intraclass correlation coefficient (ICC).

Results : In the validation dataset, the overall MAE between DLS-predicted and serum HbA1c measurements was 0.87%, the BA plot mean difference was 0.18% [95% LOA -2.39 to 2.76%], and ICC was 0.60 [95% CI 0.57-0.62, indicating fair agreement between the 2 measurements with slight overestimation by the DLS. Among diabetics, the overall MAE between the 2 measurements was 1.19%, with a BA plot mean difference of -0.57% [95% LOA -3.76 to 2.61%], showing slight underestimation by the DLS in this subgroup. On the other hand, among non-diabetic individuals, the overall MAE between the 2 measurements was 0.62%, with a BA plot mean difference of 0.69 [95% LOA -0.62 to 2.02%], showing slight overestimation by the DLS among healthy individuals.

Conclusions : We developed a novel DLS which shows early promising performance in estimating HbA1c. When further validated, this new modality may act as a new point-of-care tool for diabetic screening and monitoring.

This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.

×
×

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.

×