Open-source deep learning-based automatic segmentation of mouse Schlemm's canal in optical coherence tomography images

2021 ◽  
pp. 108844
Author(s):  
Kevin C. Choy ◽  
Guorong Li ◽  
W. Daniel Stamer ◽  
Sina Farsiu
2021 ◽  
Vol 11 (12) ◽  
pp. 5488
Author(s):  
Wei Ping Hsia ◽  
Siu Lun Tse ◽  
Chia Jen Chang ◽  
Yu Len Huang

The purpose of this article is to evaluate the accuracy of the optical coherence tomography (OCT) measurement of choroidal thickness in healthy eyes using a deep-learning method with the Mask R-CNN model. Thirty EDI-OCT of thirty patients were enrolled. A mask region-based convolutional neural network (Mask R-CNN) model composed of deep residual network (ResNet) and feature pyramid networks (FPNs) with standard convolution and fully connected heads for mask and box prediction, respectively, was used to automatically depict the choroid layer. The average choroidal thickness and subfoveal choroidal thickness were measured. The results of this study showed that ResNet 50 layers deep (R50) model and ResNet 101 layers deep (R101). R101 U R50 (OR model) demonstrated the best accuracy with an average error of 4.85 pixels and 4.86 pixels, respectively. The R101 ∩ R50 (AND model) took the least time with an average execution time of 4.6 s. Mask-RCNN models showed a good prediction rate of choroidal layer with accuracy rates of 90% and 89.9% for average choroidal thickness and average subfoveal choroidal thickness, respectively. In conclusion, the deep-learning method using the Mask-RCNN model provides a faster and accurate measurement of choroidal thickness. Comparing with manual delineation, it provides better effectiveness, which is feasible for clinical application and larger scale of research on choroid.


2018 ◽  
Vol 10 (2) ◽  
pp. 184-187
Author(s):  
Kevin Gillmann ◽  
Giorgio Enrico Bravetti ◽  
Kaweh Mansouri ◽  
André Mermoud

Introduction: The iStent inject® (Glaukos Corporation, CA, USA) is a relatively new device designed to be implanted ab-interno through the trabecular meshwork. This is, to the best of our knowledge, the first in-vivo description of a trabecular bypass device visualised with anterior segment optical coherence tomography (AS-OCT), and report of its structural effect on Schlemm’s canal. Case Report: A 74 year-old female patient suffering from long-standing primary open-angle glaucoma and nuclear sclerosis underwent cataract surgery combined with the implantation of two iStent injects®. Surgery was uncomplicated and achieved intraocular pressure (-1 mmHg) and medication (-2 molecules) reduction at 6 months. Under AS-OCT (Spectralis OCT, Heidelberg Engineering AG, Germany) the stent appears as a 300 μm long hyper reflective hollow device within the trabecular meshwork. Approximately a third of it protruded into the anterior chamber. Profound OCT signal loss was notable within the shadow of the device. A second AS-OCT section 500 μm beside the microstent shows a markedly dilated Schlemm’s canal, with a major diameter of 390 μm. Discussions: This report confirms that AS-OCT is a suitable technique to assess microstent positioning, and provides a first report on the in-vivo appearance of a functioning stent. It also indicates that iStent injects® could have a tangible effect on adjacent portions of Schlemm’s canal with, in this case, a 220% increase in canal diameter compared to the observed average (122 μm). This suggests the IOP-lowering effect of trabecular bypass devices could rely on a  dual mechanism involving Schlemm’s canal dilatation.


2010 ◽  
Vol 51 (8) ◽  
pp. 4054 ◽  
Author(s):  
Larry Kagemann ◽  
Gadi Wollstein ◽  
Hiroshi Ishikawa ◽  
Richard A. Bilonick ◽  
Peter M. Brennen ◽  
...  

2016 ◽  
Vol 94 (8) ◽  
pp. e688-e692 ◽  
Author(s):  
Serhat Imamoglu ◽  
Mehmet S. Sevim ◽  
Oksan Alpogan ◽  
Nimet Y. Ercalik ◽  
Esra Turkseven Kumral ◽  
...  

Author(s):  
Menglin Guo ◽  
Mei Zhao ◽  
Allen M. Y. Cheong ◽  
Houjiao Dai ◽  
Andrew K. C. Lam ◽  
...  

AbstractAn accurate segmentation and quantification of the superficial foveal avascular zone (sFAZ) is important to facilitate the diagnosis and treatment of many retinal diseases, such as diabetic retinopathy and retinal vein occlusion. We proposed a method based on deep learning for the automatic segmentation and quantification of the sFAZ in optical coherence tomography angiography (OCTA) images with robustness to brightness and contrast (B/C) variations. A dataset of 405 OCTA images from 45 participants was acquired with Zeiss Cirrus HD-OCT 5000 and the ground truth (GT) was manually segmented subsequently. A deep learning network with an encoder–decoder architecture was created to classify each pixel into an sFAZ or non-sFAZ class. Subsequently, we applied largest-connected-region extraction and hole-filling to fine-tune the automatic segmentation results. A maximum mean dice similarity coefficient (DSC) of 0.976 ± 0.011 was obtained when the automatic segmentation results were compared against the GT. The correlation coefficient between the area calculated from the automatic segmentation results and that calculated from the GT was 0.997. In all nine parameter groups with various brightness/contrast, all the DSCs of the proposed method were higher than 0.96. The proposed method achieved better performance in the sFAZ segmentation and quantification compared to two previously reported methods. In conclusion, we proposed and successfully verified an automatic sFAZ segmentation and quantification method based on deep learning with robustness to B/C variations. For clinical applications, this is an important progress in creating an automated segmentation and quantification applicable to clinical analysis.


Sign in / Sign up

Export Citation Format

Share Document