Investigative Ophthalmology & Visual Science Cover Image for Volume 60, Issue 9
July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
Anomaly Detection Based on Uncertainty of Retinal Layer Boundary Segmentation in OCT Images using Deep Learning
Author Affiliations & Notes
  • Sohei Miyazaki
    NIDEK Co., LTD., Gamagori, Japan
  • Ryosuke Shiba
    NIDEK Co., LTD., Gamagori, Japan
  • Naoki Takeno
    NIDEK Co., LTD., Gamagori, Japan
  • Yoshiki Kumagai
    NIDEK Co., LTD., Gamagori, Japan
  • Yusuke SAKASHITA
    NIDEK Co., LTD., Gamagori, Japan
  • Naohisa Shibata
    NIDEK Co., LTD., Gamagori, Japan
  • Footnotes
    Commercial Relationships   Sohei Miyazaki, NIDEK Co., LTD. (E); Ryosuke Shiba, NIDEK Co., LTD. (E); Naoki Takeno, NIDEK Co., LTD. (E); Yoshiki Kumagai, NIDEK Co., LTD. (E); Yusuke SAKASHITA, NIDEK Co., LTD. (E); Naohisa Shibata, NIDEK Co., LTD. (E)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1500. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Sohei Miyazaki, Ryosuke Shiba, Naoki Takeno, Yoshiki Kumagai, Yusuke SAKASHITA, Naohisa Shibata; Anomaly Detection Based on Uncertainty of Retinal Layer Boundary Segmentation in OCT Images using Deep Learning. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1500.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : OCT is rapidly becoming the standard of care for ophthalmic diagnosis. However, ocular abnormalities can be overlooked during clinical examination especially when several images are obtained during a single image capture. Hence, automated detection of ocular abnormalities from OCT images is actively developed for. We propose an abnormality detection method using segmentation of OCT images of normal eyes, and report its effectiveness.

Methods : We focused on the differences in the difficulty of segmenting OCT images of normal eyes and those containing abnormal regions. An abnormality in OCT images appears as a disrupted retinal layer structure due to disease. When image processing designed for normal retinal layer structure is applied, segmentation of OCT images that contain abnormal portions is considered more difficult than that of OCT images of normal eyes. We propose a model that performs segmentation of OCT images using deep learning. We visualized the degree of abnormality of the retinal structure by quantifying the deviation in the probability distribution output by the proposed model as “uncertainty”. When the model is trained only with OCT images of normal eyes, segmentation of the OCT images containing abnormal portions is difficult, and the uncertainty value is expected increase.

Results : Twenty OCT images of normal eyes captured with the RS-3000 Advance (Nidek, Aichi, Japan) were used to train the model by deep learning. Then, 32 OCT images of normal eyes and 80 OCT images of diseased eyes were input to the model to obtain the uncertainty values. The obtained uncertainty was 12.70±0.40 for normal eyes, and 16.38±2.09 for diseased eyes. Although the data set was small, the model distinguished between normal eyes and diseased eyes with high accuracy (AUC=0.99). Additionally, there was confirmation that areas with a high uncertainty matched the abnormal regions.

Conclusions : We present a method to detect retinal abnormalities by quantifying the deviation in the probability distribution output by a model trained by deep learning. This was achieved by focusing on the difference in the difficulty of segmentation that becomes conspicuous between OCT images of normal eyes and those containing abnormal regions. This method can be developed by training the model with OCT images of normal eyes only.

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.

×