Chen Yu Lin1, Yu Len Huang2, Wei Ping Hsia1, Yang Wang2, Chia Jen Chang3,4. 1. Department of Ophthalmology, Taichung Veterans General Hospital, No.1650, Sec. 4, Taiwan Blvd., Situn Dist., Taichung, Taiwan. 2. Department of Computer Science, Tunghai University, Taichung, Taiwan. 3. Department of Ophthalmology, Taichung Veterans General Hospital, No.1650, Sec. 4, Taiwan Blvd., Situn Dist., Taichung, Taiwan. capmchangcj@gmail.com. 4. Department of Optometry, Central Taiwan University of Science and Technology, Taichung, Taiwan. capmchangcj@gmail.com.
Abstract
PROPOSE: The proposed deep learning model with a mask region-based convolutional neural network (Mask R-CNN) can predict choroidal thickness automatically. Changes in choroidal thickness with age can be detected with manual measurements. In this study, we aimed to investigate choroidal thickness in a comprehensive aspect in healthy eyes by utilizing the Mask R-CNN model. METHODS: A total of 68 eyes from 57 participants without significant ocular disease were recruited. The participants were allocated to one of three groups according to their age and underwent spectral domain optical coherence tomography (SD-OCT) or enhanced depth imaging OCT (EDI-OCT) centered on the fovea. Each OCT sequence included 25 slices. Physicians labeled the choroidal contours in all the OCT sequences. We applied the Mask R-CNN model for automatic segmentation. Comparisons of choroidal thicknesses were conducted according to age and prediction accuracy. RESULTS: Older age groups had thinner choroids, according to the automatic segmentation results; the mean choroidal thickness was 253.7 ± 41.9 μm in the youngest group, 206.8 ± 35.4 μm in the middle-aged group, and 152.5 ± 45.7 μm in the oldest group (p < 0.01). Measurements obtained using physician sketches demonstrated similar trends. We observed a significant negative correlation between choroidal thickness and age (p < 0.01). The prediction error was lower and less variable in choroids that were thinner than the cutoff point of 280 μm. CONCLUSION: By observing choroid layer continuously and comprehensively. We found that the mean choroidal thickness decreased with age in healthy subjects. The Mask R-CNN model can accurately predict choroidal thickness, especially choroids thinner than 280 μm. This model can enable exploring larger and more varied choroid datasets comprehensively, automatically, and conveniently.
PROPOSE: The proposed deep learning model with a mask region-based convolutional neural network (Mask R-CNN) can predict choroidal thickness automatically. Changes in choroidal thickness with age can be detected with manual measurements. In this study, we aimed to investigate choroidal thickness in a comprehensive aspect in healthy eyes by utilizing the Mask R-CNN model. METHODS: A total of 68 eyes from 57 participants without significant ocular disease were recruited. The participants were allocated to one of three groups according to their age and underwent spectral domain optical coherence tomography (SD-OCT) or enhanced depth imaging OCT (EDI-OCT) centered on the fovea. Each OCT sequence included 25 slices. Physicians labeled the choroidal contours in all the OCT sequences. We applied the Mask R-CNN model for automatic segmentation. Comparisons of choroidal thicknesses were conducted according to age and prediction accuracy. RESULTS: Older age groups had thinner choroids, according to the automatic segmentation results; the mean choroidal thickness was 253.7 ± 41.9 μm in the youngest group, 206.8 ± 35.4 μm in the middle-aged group, and 152.5 ± 45.7 μm in the oldest group (p < 0.01). Measurements obtained using physician sketches demonstrated similar trends. We observed a significant negative correlation between choroidal thickness and age (p < 0.01). The prediction error was lower and less variable in choroids that were thinner than the cutoff point of 280 μm. CONCLUSION: By observing choroid layer continuously and comprehensively. We found that the mean choroidal thickness decreased with age in healthy subjects. The Mask R-CNN model can accurately predict choroidal thickness, especially choroids thinner than 280 μm. This model can enable exploring larger and more varied choroid datasets comprehensively, automatically, and conveniently.
Authors: Daniel Ian Flitcroft; Mingguang He; Jost B Jonas; Monica Jong; Kovin Naidoo; Kyoko Ohno-Matsui; Jugnoo Rahi; Serge Resnikoff; Susan Vitale; Lawrence Yannuzzi Journal: Invest Ophthalmol Vis Sci Date: 2019-02-28 Impact factor: 4.799
Authors: Chui Ming Gemmy Cheung; Won Ki Lee; Hideki Koizumi; Kunal Dansingani; Timothy Y Y Lai; K Bailey Freund Journal: Eye (Lond) Date: 2018-07-11 Impact factor: 3.775