June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Deep learning based binary image quality algorithm for low-cost fundus imaging system in remote care settings
Author Affiliations & Notes
  • Taylor Shagam
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Minhaj Alam
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Simon Bello
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Laura Tracewell
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Bryan Rogoff
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Patricia Sha
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Noli Graves
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Dorothy Hitchmoth
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Mary K Durbin
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Niranchana Manivannan
    Carl Zeiss Meditec Inc, Dublin, California, United States
  • Footnotes
    Commercial Relationships   Taylor Shagam, Carl Zeiss Meditec, Inc. (E); Minhaj Alam, Carl Zeiss Meditec, Inc. (C); Simon Bello, Carl Zeiss Meditec, Inc. (E); Laura Tracewell, Carl Zeiss Meditec, Inc. (C); Bryan Rogoff, Carl Zeiss Meditec, Inc. (E); Patricia Sha, Carl Zeiss Meditec, Inc. (C); Noli Graves, Carl Zeiss Meditec, Inc. (C); Dorothy Hitchmoth, Carl Zeiss Meditec, Inc. (C); Mary Durbin, Carl Zeiss Meditec, Inc. (E); Niranchana Manivannan, Carl Zeiss Meditec, Inc. (E)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 100. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Taylor Shagam, Minhaj Alam, Simon Bello, Laura Tracewell, Bryan Rogoff, Patricia Sha, Noli Graves, Dorothy Hitchmoth, Mary K Durbin, Niranchana Manivannan; Deep learning based binary image quality algorithm for low-cost fundus imaging system in remote care settings. Invest. Ophthalmol. Vis. Sci. 2021;62(8):100.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : An image quality (IQ) algorithm is important in assisting medical assistants with little to no experience in ophthalmology to judge whether an image is of sufficient quality for clinical diagnosis.
In this study, we developed a binary IQ classification for providing real-time feedback in a remote care or primary care settings.

Methods : Data:
5173 images acquired using VELARA™ 200 (Zeiss, Dublin, CA) camera from a retrospective study were graded by 2 graders and adjudicated by an optometrist). The images were acquired from normal and diseased subjects with various retinal pathologies were graded for quality of readable clinical information in a 1-5 scale (1-very poor and5-xcellent). The ground truth (GT) is determined by converting the gradings to binary: 0- Insufficient if IQ is <=2 (65.6% of 5173 images) and 1-Sufficient if IQ is >2 (34.4%). Small pupils, incorrect fixation, out of focus and other artifacts were the main causes of insufficient IQ.

Algorithm:
The dataset is split into three: i) training- 3646, ii) validation- 928 and iii) hold-out test – 599. The training set is augmented using flip and brightness adjustments. The deep learning architectures used to train the IQ classification are shown in figure 1. ImageNet weights were preloaded, sigmoid activation with binary cross entropy loss were used. The data was resampled and reweighted to account for the class imbalance. For hyperparameter tuning, all the networks were trained using Adam with cyclic learning rate scheduler and Stochastic Gradient Descent (SGD) with Nesterov momentum. SGD with Nesterov is chosen for the final model as it performed better. Sensitivity, specificity and the execution time were compared to select the final IQ model.

Results : The performance of all networks in hold-out test set is shown in Figure 1. VGG-16 provided high sensitivity, specificity with lower execution time is selected as the final model. It achieved 99% sensitivity, 91% specificity and 220ms execution time in i5-10400H CPU. Figure 2 shows some of the examples results from IQ algorithm.

Conclusions : We developed an image quality algorithm with 99% sensitivity with an execution time to provide real-time feedback to the operator on whether to retake the fundus images.

This is a 2021 ARVO Annual Meeting abstract.

 

Figure 2. Sample results from proposed algorithm

Figure 2. Sample results from proposed algorithm

 

Figure 1. a)Performance of various models b)ROC curve from final model

Figure 1. a)Performance of various models b)ROC curve from final model

×
×

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.

×