Abstract

The aim of the current study is to identify possible new Ocular Response Analyzer (ORA) waveform parameters related to changes of retinal structure/deformation, as measured by the peripapillary retinal arteries angle (PRAA), using a generative deep learning method of variational autoencoder (VAE). Fifty-four eyes of 52 subjects were enrolled. The PRAA was calculated from fundus photographs and was used to train a VAE model. By analyzing the ORA waveform reconstructed (noise filtered) using VAE, a novel ORA waveform parameter (Monot1-2), was introduced, representing the change in monotonicity between the first and second applanation peak of the waveform. The variables mostly related to the PRAA were identified from a set of 41 variables including age, axial length (AL), keratometry, ORA corneal hysteresis, ORA corneal resistant factor, 35 well established ORA waveform parameters, and Monot1-2, using a model selection method based on the second-order bias-corrected Akaike information criterion. The optimal model for PRAA was the AL and six ORA waveform parameters, including Monot1-2. This optimal model was significantly better than the model without Monot1-2 (p = 0.0031, ANOVA). The current study suggested the value of a generative deep learning approach in discovering new useful parameters that may have clinical relevance.

Details

Title
Visualizing the dynamic change of Ocular Response Analyzer waveform using Variational Autoencoder in association with the peripapillary retinal arteries angle
Author
Asano Shotaro 1 ; Asaoka Ryo 2 ; Yamashita Takehiro 3   VIAFID ORCID Logo  ; Aoki Shuichiro 1 ; Matsuura Masato 4 ; Fujino, Yuri 5   VIAFID ORCID Logo  ; Murata, Hiroshi 1 ; Nakakura Shunsuke 6 ; Nakao Yoshitaka 7 ; Kiuchi Yoshiaki 7   VIAFID ORCID Logo 

 Graduate School of Medicine and Faculty of Medicine, The University of Tokyo, Department of Ophthalmology, Tokyo, Japan (GRID:grid.26999.3d) (ISNI:0000 0001 2151 536X) 
 Graduate School of Medicine and Faculty of Medicine, The University of Tokyo, Department of Ophthalmology, Tokyo, Japan (GRID:grid.26999.3d) (ISNI:0000 0001 2151 536X); Seirei General Hospital, Shizuoka, Japan (GRID:grid.26999.3d); Seirei Christopher University, Shizuoka, Japan (GRID:grid.443623.4) (ISNI:0000 0004 0373 7825) 
 Kagoshima University Graduate School of Medical and Dental Sciences, Kagoshima, Japan (GRID:grid.258333.c) (ISNI:0000 0001 1167 1801) 
 Graduate School of Medicine and Faculty of Medicine, The University of Tokyo, Department of Ophthalmology, Tokyo, Japan (GRID:grid.26999.3d) (ISNI:0000 0001 2151 536X); Graduate School of Medical Sciences, Kitasato University, Department of Ophthalmology, Kanagawa, Japan (GRID:grid.410786.c) (ISNI:0000 0000 9206 2938) 
 Graduate School of Medicine and Faculty of Medicine, The University of Tokyo, Department of Ophthalmology, Tokyo, Japan (GRID:grid.26999.3d) (ISNI:0000 0001 2151 536X); Seirei General Hospital, Shizuoka, Japan (GRID:grid.26999.3d); Graduate School of Medical Sciences, Kitasato University, Department of Ophthalmology, Kanagawa, Japan (GRID:grid.410786.c) (ISNI:0000 0000 9206 2938) 
 Saneikai Tsukazaki Hospital, Department of Ophthalmology, Hyogo, Japan (GRID:grid.26999.3d) 
 Hiroshima University, Department of Ophthalmology and Visual Science, Hiroshima, Japan (GRID:grid.257022.0) (ISNI:0000 0000 8711 3200) 
Publication year
2020
Publication date
2020
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2392414571
Copyright
© The Author(s) 2020. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.