June 2020
Volume 61, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2020
Deep Learning Approach for Automated Recognition of Retinal Pigment Epithelium Cell
Author Affiliations & Notes
  • Majda Hadziahmetovic
    Duke University, Durham, North Carolina, United States
  • Qitong Gao
    Duke University, Durham, North Carolina, United States
  • Ying Xu
    Duke University, Durham, North Carolina, United States
  • Joshua Amason
    Duke University, Durham, North Carolina, United States
  • Anna Loksztejn
    Duke University, Durham, North Carolina, United States
  • Scott W Cousins
    Duke University, Durham, North Carolina, United States
  • Miroslav Pajic
    Duke University, Durham, North Carolina, United States
  • Footnotes
    Commercial Relationships   Majda Hadziahmetovic, None; Qitong Gao, None; Ying Xu, None; Joshua Amason, None; Anna Loksztejn, None; Scott Cousins, None; Miroslav Pajic, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 2030. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Majda Hadziahmetovic, Qitong Gao, Ying Xu, Joshua Amason, Anna Loksztejn, Scott W Cousins, Miroslav Pajic; Deep Learning Approach for Automated Recognition of Retinal Pigment Epithelium Cell. Invest. Ophthalmol. Vis. Sci. 2020;61(7):2030.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop a deep learning-based method with limited training resources, that can automatically identify and count the number of Retinal Pigment Epithelium (RPE) cells in confocal microscopy images obtained from cell culture or mice RPE/Choroid flat-mounts.

Methods : The training and testing dataset contains two different image types: wild-type mice RPE/Choroid flat-mounts and ARPE 19 cells in culture, stained for Rhodamine-phalloidin, and imaged with confocal microscopy. Our approach is shown in Fig.1. Afterimage pre-processing for de-noising and contrast adjustment, Scale-Invariant Feature Transform descriptors are used for feature extraction. The set of training labels is derived from cells in original training images, annotated and converted to Gaussian density maps as a sum of fixed-variance Gaussians centered at each annotation. Finally, we train a Deep Neural Network (DNN) using the set of training input features and labels such that the obtained DNN model accurately predicts the corresponding Gaussian density maps, and thus identify/count the cells for any image.

Results : The training and testing dataset contains 229 images from ARPE19 and 85 images from RPE/Choroid flat-mounts. Within two data sets, 30% and 10% of the images were selected for validation. We achieved 96.48 ± 6.56% and 96.88 ± 3.68% accuracy, with 95% confidence intervals, on ARPE19 and RPE/Choroid flat-mounts samples. Our approach outperforms existing relevant methods by significantly decreasing prediction error and variance, as shown in Fig. 2.

Conclusions : We developed a deep learning-based approach that can accurately estimate the number of RPE cells contained in images obtained from cell culture and mice flat-mounts. We devised image pre-processing and data augmentation methods to form sufficient training images and improve the accuracy of the learning algorithm. Unlike existing methods that either requires a substantial number of training images or convex loss functions, our method achieves high accuracy with limited training datasets without compromising the expressiveness of the learning model. Furthermore, our approach is not limited by the cell shape of the input microscopy images and can be effectively used on images with unclear and curvy boundaries.

This is a 2020 ARVO Annual Meeting abstract.

 

Overview of our DNN-based approach

Overview of our DNN-based approach

 

Testing results summary -- sum error rate (SER), counting accuracy (ACC), C-Te and M-Te denote cell culture and mice image testing sets

Testing results summary -- sum error rate (SER), counting accuracy (ACC), C-Te and M-Te denote cell culture and mice image testing sets

×
×

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.

×