July 2019
Volume 60, Issue 9
Free
ARVO Annual Meeting Abstract  |   July 2019
Evaluation of glaucoma diagnosis machine learning models based on color optical coherence tomography and color fundus images
Author Affiliations & Notes
  • Masahiro Akiba
    R&D, Topcon Corporation, Itabashi, Tokyo, Japan
    Center for Advanced Photonics, RIKEN, Wako, Saitama, Japan
  • Guangzhou An
    R&D, Topcon Corporation, Itabashi, Tokyo, Japan
    Center for Advanced Photonics, RIKEN, Wako, Saitama, Japan
  • Hideo yokota
    Center for Advanced Photonics, RIKEN, Wako, Saitama, Japan
  • Kazuko Omodaka
    Graduate School of Medicine, Tohoku University, Sendai, Miyagi, Japan
  • Kazuki Hashimoto
    Graduate School of Medicine, Tohoku University, Sendai, Miyagi, Japan
  • Satoru Tsuda
    Graduate School of Medicine, Tohoku University, Sendai, Miyagi, Japan
  • Yukihiro Shiga
    Graduate School of Medicine, Tohoku University, Sendai, Miyagi, Japan
  • naoko takada
    Graduate School of Medicine, Tohoku University, Sendai, Miyagi, Japan
  • tsutomu kikawa
    R&D, Topcon Corporation, Itabashi, Tokyo, Japan
  • Toru Nakazawa
    Graduate School of Medicine, Tohoku University, Sendai, Miyagi, Japan
  • Footnotes
    Commercial Relationships   Masahiro Akiba, Topcon (E); Guangzhou An, Topcon Corporation (E); Hideo yokota, None; Kazuko Omodaka, None; Kazuki Hashimoto, None; Satoru Tsuda, None; Yukihiro Shiga, None; naoko takada, None; tsutomu kikawa, Topcon Corporation (E); Toru Nakazawa, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1298. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Masahiro Akiba, Guangzhou An, Hideo yokota, Kazuko Omodaka, Kazuki Hashimoto, Satoru Tsuda, Yukihiro Shiga, naoko takada, tsutomu kikawa, Toru Nakazawa; Evaluation of glaucoma diagnosis machine learning models based on color optical coherence tomography and color fundus images. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1298.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop and evaluate deep learning based glaucoma diagnosis models, based on optical coherence tomography (OCT) data and color fundus images, aiming for clinical use.

Methods : This study included 149 healthy (MD: -0.21±1.15 dB) and 208 open-angle glaucoma (OAG) (MD: -3.90±3.80 dB) eyes. All these eyes were captured with spectral-domain OCT (3D OCT-2000, Topcon), in protocol of macular and disc volumetric scans, as well as color fundus images. With the commercial OCT segmentation software, we created retinal nerve fiber layer (RNFL) thickness map from disc volumetric OCT data, and ganglion cell complex (GCC) thicknees map from macular volumetric OCT data. First, with the created images we transfer learned 3 separate convolutional neural network (CNN) models with well-known architecure of VGG19, which were pre-trained on ImageNet dataset. With these VGG19 models as feature extractors, images features were obtained in the top level of VGG19s for each kind of images, and concatenated for training a random forest (RF) to combine separate models. The area under receiver operating characteristic curve (AUC) of a 10-fold cross-validation (CV) was applied to evaluate our models.

Results : The 10-fold AUCs of the VGG19 models were 0.940 for color fundus images, 0.942 for cpRNFL thickness map, 0.944 for macular GCC thickness maps. The RF using all kinds of images achieved the highest 10-fold CV AUC of 0.961. We found by adjusting the threshold, our model got an excellent sensitivity for detecting glaucoma, with acceptable false positive ratio.

Conclusions : Our proposed approach was efficient for automatic classification of healthy and glaucoma eyes based on OCT and color fundus images, and it might be used in assisting glaucoma diagnosis. The optimized threshold for our model in clinical use should be determined for our future work.

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.

×