June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Automatic identification and quantification of retinal cysts in optical coherence tomography images using deep residual encoder-decoder architecture.
Author Affiliations & Notes
  • Shanmukh Reddy Manne
    Electrical Engineering, Indian Institute of Technology Hyderabad, Hyderabad, Telangana, India
  • Amrish Selvam
    University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States
  • Manan Patel
    BJ Medical College, Ahmedabad, Gujarat, India
  • Arnim Kuchhal
    Fox Chapel High School, Pittsburgh, Pennsylvania, United States
  • Jose Alain Sahel
    University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States
  • Jay Chhablani
    University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States
  • Kiran Kumar Vupparaboina
    University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States
  • Soumya Jana
    Electrical Engineering, Indian Institute of Technology Hyderabad, Hyderabad, Telangana, India
  • Footnotes
    Commercial Relationships   Shanmukh Reddy Manne None; Amrish Selvam None; Manan Patel None; Arnim Kuchhal None; Jose Sahel GENSIGHT-BIOLOGICS.COM, Code C (Consultant/Contractor); Jay Chhablani None; Kiran Vupparaboina None; Soumya Jana None
  • Footnotes
    Support  This work was supported by NIH CORE Grant P30 EY08098 to the Department of Ophthalmology, the Eye and Ear Foundation of Pittsburgh, and from an unrestricted grant from Research to Prevent Blindness, New York, NY.
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 2082 – F0071. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Shanmukh Reddy Manne, Amrish Selvam, Manan Patel, Arnim Kuchhal, Jose Alain Sahel, Jay Chhablani, Kiran Kumar Vupparaboina, Soumya Jana; Automatic identification and quantification of retinal cysts in optical coherence tomography images using deep residual encoder-decoder architecture.. Invest. Ophthalmol. Vis. Sci. 2022;63(7):2082 – F0071.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Retinal cysts or fluid spaces accumulated between different layers of eye are key signatures of diseases like age-related macular degeneration (AMD) and macular edema (ME). Accordingly, for accurate screening and disease management, clinicians seek to quantify these lesions using ubiquitous optical coherence tomography (OCT) scans. However, manual delineation is tedious and may induce errors. In response, attempts were made towards automated quantification based on imag processing and machine learning approaches. However, the detection accuracy is still sub-optimal and has scope for improvement. Against this backdrop, we attempt to build a robust fluid segmentation tool leveraging a pre-trained encoder-decoder architecture with residual network (ResNet) at the encoder that was proven to be effective in other segmentation tasks by preserving features across layers.

Methods : This is a retrospective study consisting of 3175 OCT scans (1048 with fluid/cysts and 2127 without any lesions) taken from wide-field swept-source optical coherence tomography (OCT) device (Carl Zeiss Plex Elite 9000) with a resolution of 12mm×3mm. The presence of fluid was detected based on our previously validated XGBoost algorithm. We employed ResUNet deep-learning architecture which uses residual network at the encoder (see Fig. 1). Masks required to train the model were obtained by manually labeling fluid regions by a trained expert using the ImageJ tool. Dataset is randomly partitioned into training and testing (unseen) sets with a split-ratio of 90:10. Finally, the OCT scans were resized to (256, 256) and the model was trained using Dice coefficient as loss function (epochs: 80, batch size: 16).

Results : The proposed method achieves an averaged Dice score of 91.47% against ground truth segmentations and outperforms the existing UNet based approaches as well. Fig. 2 depicts representative test OCT images with both manual as well as algorithmic segmentation and also provides volumetric quantification of cysts in 3D volume for a subject.

Conclusions : The proposed approach achieves segmentation accuracy close to trained optometrists. Next, we are working towards extending this to identify different types of fluids and also perform voxel-level segmentation that enables volumetric quantification of retinal cysts.

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

 

Schematic flow of proposed approach

Schematic flow of proposed approach

 

Segmentation Results

Segmentation Results

×
×

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.

×