Deep learning algorithms to isolate and quantify the structures of the anterior segment in optical coherence tomography images

@article{Pham2020DeepLA,
  title={Deep learning algorithms to isolate and quantify the structures of the anterior segment in optical coherence tomography images},
  author={Tan Hung Pham and Sripad Krishna Devalla and A Ang and Zhi Da Soh and Alexandre Hoang Thiery and Craig Boote and Ching-Yu Cheng and Michael J. A. Girard and Victor Tc Koh},
  journal={British Journal of Ophthalmology},
  year={2020},
  volume={105},
  pages={1231 - 1237}
}
Background/Aims Accurate isolation and quantification of intraocular dimensions in the anterior segment (AS) of the eye using optical coherence tomography (OCT) images is important in the diagnosis and treatment of many eye diseases, especially angle-closure glaucoma. Method In this study, we developed a deep convolutional neural network (DCNN) for the localisation of the scleral spur; moreover, we introduced an information-rich segmentation approach for this localisation problem. An ensemble… 
Reproducibility of deep learning based scleral spur localisation and anterior chamber angle measurements from anterior segment optical coherence tomography images
TLDR
D LLSS achieved comparable repeatability compared with MPSS for measurement of anterior chamber angle (ACA) width between deep learning located SS (DLLSS) and manually plotted SS (MPSS), and the repeatability of ACA width was measured.
Towards Label-Free 3D Segmentation of Optical Coherence Tomography Images of the Optic Nerve Head Using Deep Learning
TLDR
A DL-based 3D segmentation framework that is easily translatable across OCT devices in a label-free manner (i.e. without the need to manually re-segment data for each device) is proposed.
Automatic segmentation of intraocular lens, the retrolental space and Berger's space using deep learning.
TLDR
The deep learning model allows for fully automatic segmentation of all investigated structures, achieving human-level performance in BS segmentation, and is expected to expect promising applications of the algorithm with particular interest in BS in automated big data analysis and real-time intra-operative support in ophthalmology.
Multilevel CNN for Angle Closure Glaucoma Detection using AS-OCT Images
TLDR
A method for automatic detection of angle closure glaucoma in anterior segment optical coherence tomography images is proposed, based on transfer learning and multilevel convolutional neural networks to extract visual features.
Anterior Chamber Angle Assessment Techniques: A Review
TLDR
This review summarizes the last findings in ACA evaluation, focusing on new instruments and their application to the clinical practice, and the comparison between these new techniques and traditional slit-lamp gonioscopy.
Artificial intelligence for anterior segment diseases: Emerging applications in ophthalmology
TLDR
An overview of AI applications to the anterior segment addressing keratoconus, infectious keratitis, refractive surgery, corneal transplant, adult and paediatric cataracts, angle-closure glaucoma and iris tumour is provided and important clinical considerations for adoption of AI technologies, potential integration with telemedicine and future directions are highlighted.
Optimal number and orientation of anterior segment OCT images to measure ocular biometric parameters in angle closure eyes: the Chinese American Eye Study
TLDR
S Sectoral anatomical variations in angle closure eyes are easily misrepresented based on current AS-OCT imaging conventions, so a revised multi-image approach can better capture the mean and range of biometric measurements.

References

SHOWING 1-10 OF 60 REFERENCES
A Deep Learning Approach to Digitally Stain Optical Coherence Tomography Images of the Optic Nerve Head
TLDR
The authors' deep learning algorithm can simultaneously stain the neural and connective tissues of the OnH, offering a framework to automatically measure multiple key structural parameters of the ONH that may be critical to improve glaucoma management.
DRUNET: A Dilated-Residual U-Net Deep Learning Network to Digitally Stain Optic Nerve Head Tissues in Optical Coherence Tomography Images
TLDR
A robust segmentation framework is offered that could also be extended to the 3D segmentation of the ONH tissues and automatically extracted six clinically relevant neural and connective tissue structural parameters from the segmented tissues.
Assessment of the scleral spur in anterior segment optical coherence tomography images.
TLDR
The inability to detect the scleral spur may hamper quantitative analysis of anterior chamber angle parameters that are dependent on the location of this anatomical structure, particularly in the superior and inferior quadrants.
The Effect of Scleral Spur Identification Methods on Structural Measurements by Anterior Segment Optical Coherence Tomography
TLDR
The CM method was the most successful and least variable method of SS marking, which was more difficult in narrow angle and brown eyes, and had a large effect on angle parameters and iris concavity ratio.
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Detecting Anatomical Landmarks From Limited Medical Imaging Data Using Two-Stage Task-Oriented Deep Neural Networks
TLDR
A two-stage task-oriented deep learning method to detect large-scale anatomical landmarks simultaneously in real time, using limited training data, consisting of two deep convolutional neural networks, with each focusing on one specific task.
Association of narrow angles with anterior chamber area and volume measured with anterior-segment optical coherence tomography.
TLDR
Smaller anterior chamber area and anterior chamber volume were independently associated with narrow angles in Singaporeans, even after controlling for other known ocular risk factors.
Reproducibility of Scleral Spur Identification and Angle Measurements Using Fourier Domain Anterior Segment Optical Coherence Tomography
Purpose. To evaluate intraobserver and interobserver agreement in locating the scleral spur landmark (SSL) and anterior chamber angle measurements obtained using Fourier Domain Anterior Segment
...
...