July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
Automatic detection of retinal fluid in OCT volumes
Author Affiliations & Notes
  • Pablo Márquez Neila
    ARTORG, University of Bern, Bern, Canton of Bern, Switzerland
  • Thomas Kevin Kurmann
    ARTORG, University of Bern, Bern, Canton of Bern, Switzerland
  • Siqing Yu
    Department of Ophthalmology, Bern University Hospital, Bern, Canton of Bern, Switzerland
  • Marion Ronit Munk
    Department of Ophthalmology, Bern University Hospital, Bern, Canton of Bern, Switzerland
    Ophthalmology, Northwestern University, Feinberg School of Medicine, Chicago, Illinois, United States
  • Sebastian Wolf
    Department of Ophthalmology, Bern University Hospital, Bern, Canton of Bern, Switzerland
  • Raphael Sznitman
    ARTORG, University of Bern, Bern, Canton of Bern, Switzerland
  • Footnotes
    Commercial Relationships   Pablo Márquez Neila, None; Thomas Kurmann, None; Siqing Yu, None; Marion Munk, Bayer (F), Gensight (C), Lumithera (C), Zeiss (C); Sebastian Wolf, Bayer (C), Heidelberg (C), Novartis (C), Zeiss (C); Raphael Sznitman, RetinAI Medical AG (C)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1518. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Pablo Márquez Neila, Thomas Kevin Kurmann, Siqing Yu, Marion Ronit Munk, Sebastian Wolf, Raphael Sznitman; Automatic detection of retinal fluid in OCT volumes. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1518.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Fluid in the retina plays a critical role in managing chronic retinal conditions. OCT volumetric scans are key in assessing if such fluid is present or not. We hypothesize that this task is suitable for automation using machine learning techniques. Moreover, we speculate that training a machine learning model for this task requires only manual annotations regarding the presence of fluid, as opposed to pixel-wise annotations of fluid regions. This would render easier and cheaper annotations for machine learning tasks.

Methods : We use two datasets of OCT C-Scans. The first dataset (D1) consists of 1201 OCT volumes from 130~subjects who suffer from different stages of AMD. 519 (43%) volumes were manually labeled as dry and 682 (57%) volumes were labeled as wet. The second dataset (D2) consists of 983 C-Scans from a mixed subject pool of 723 eyes (AMD, DR, DME, CVO). 268 (27%) volumes were labeled as dry, and 715 (73%) were labeled as wet. Volumes were acquired using the Heidelberg Engineering Spectralis OCT system. All volumes are processed by our machine learning architecture in the same manner. Given a volume, its B-Scans are resized and separately fed to a Dilated Residual Network (DRN-D-54). B-Scan descriptions are merged together in a single volume signature, which is further processed to obtain the probability of finding fluid in the volume. The whole network is trained end-to-end using the dataset D1. After training, network is tested using the dataset D2.

Results : The area under the ROC curve is 0.939 and the area under the precision-recall curve is 0.977. For a specificity of 0.9, we attain a sensitivity of 0.88. For a sensitivity of 0.95, we obtain a specificity of 0.57. Our deep network processes an entire volume in 1.23 seconds with test-time augmentation. Without test-time augmentation, computation time per volume is reduced to 0.31 seconds with a minor reduction in performance, with the sensitivity dropping to 0.86 for a specificity of 0.9.

Conclusions : Our experimental results successfully support our hypothesis for the automation of retinal fluid detection. Our deep network is able to learn the visual appearance of fluid just using human annotations given at the C-Scan level, which are cheap to obtain. Our method has potential to save time and work to clinicians, while being reliable and consistent.

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

 

ROC curve of our method. Marked points correspond to the performance at specificity of 0.9 and sensitivity of 0.95.

ROC curve of our method. Marked points correspond to the performance at specificity of 0.9 and sensitivity of 0.95.

×
×

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.

×