Robust Retinal Layer Segmentation Using OCT B-Scans: A Novel Approach Based on Pix2Pix Generative Adversarial Network
Authors: 
Adarsh Gadari, Sandeep Chandra Bollepalli, Mohammed Nasar Ibrahim, Sahel Jose´-Alian, Jay Chhablani, Shan Suthaharan, Kiran Kumar VupparaboinaAuthors Info & Claims
Article No.: 52, Pages 1 - 6
Abstract
Various eye diseases, such as age-related macular degeneration (AMD), are caused due to the structural dysfunction of the retinal sublayers. In the current clinical practice, clinicians screen ubiquitous optical coherence tomography (OCT) scans to visualize the retina's structural changes and diagnose the associated diseases. Quantitative assessment of such structural changes assumes significance in accurate disease management and treatment response monitoring. To this end, various attempts based on image processing, machine learning, and deep learning methods have been reported. However, they have not fully leveraged the unique structural characteristics of retinal sublayers in OCT B-Scans. In this work, we proposed a Pix2Pix-GAN-based algorithm capable of synthesizing look-alike target images from source images by mapping pixel-wise structural information. In particular, we envisioned the Pix2Pix network to synthesize OCT images with each boundary of interest labeled in the same color as the corresponding boundary in ground-truth images. On a dataset of 180 EDI OCT B-Scans with accurate ground-truth segmentation for six retinal sublayer boundaries, we trained and tested the Pix2Pix-GAN model. In particular, we achieved an overall mean Dice coefficient of 96.84 % and 96.85 %, respectively, for train and test dataset, indicating close agreement between ground-truth and proposed Pix2Pix-GAN-based segmentation.
References
[1]
Annie Chan, Jay S Duker, Hiroshi Ishikawa, Tony H Ko, Joel S Schuman, and James G Fujimoto. 2006. Quantification of photoreceptor layer thickness in normal eyes using optical coherence tomography. Retina (Philadelphia, Pa.) 26, 6 (2006), 655.
[2]
Stephanie J Chiu, Xiao T Li, Peter Nicholas, Cynthia A Toth, Joseph A Izatt, and Sina Farsiu. 2010. Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation. Optics express 18, 18 (2010), 19413--19428.
[3]
Özgün Çiçek, Ahmed Abdulkadir, Soeren S. Lienkamp, Thomas Brox, and Olaf Ronneberger. 2016. 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016, Sebastien Ourselin, Leo Joskowicz, Mert R. Sabuncu, Gozde Unal, and William Wells (Eds.). Springer International Publishing, Cham, 424--432.
[4]
William S Cleveland and Susan J Devlin. 1988. Locally weighted regression: an approach to regression analysis by local fitting. Journal of the American statistical association 83, 403 (1988), 596--610.
[5]
Bo Dai, Sanja Fidler, Raquel Urtasun, and Dahua Lin. 2017. Towards diverse and natural image descriptions via a conditional gan. In Proceedings of the IEEE international conference on computer vision. 2970--2979.
[6]
Lee R. Dice. 1945. Measures of the Amount of Ecologic Association Between Species. In Ecology, Vol. 26. 297--302.
[7]
Leyuan Fang, David Cunefare, Chong Wang, Robyn H Guymer, Shutao Li, and Sina Farsiu. 2017. Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search. Biomedical optics express 8, 5 (2017), 2732--2744.
[8]
Alfred Fuller, Robert Zawadzki, Stacey Choi, David Wiley, John Werner, and Bernd Hamann. 2007. Segmentation of three-dimensional retinal image data. IEEE transactions on visualization and computer graphics 13, 6 (2007), 1719--1726.
[9]
Google LLC. 2020. TensorFlow. [Software]. https://www.tensorflow.org/
[10]
Karthik Gopinath, Samrudhdhi B Rangrej, and Jayanthi Sivaswamy. 2017. A deep learning framework for segmentation of retinal layers from OCT images. In 2017 4th IAPR Asian conference on pattern recognition (ACPR). IEEE, 888--893.
[11]
Michael R Hee, Joseph A Izatt, Eric A Swanson, David Huang, Joel S Schuman, Charles P Lin, Carmen A Puliafito, and James G Fujimoto. 1995. Optical coherence tomography of the human retina. Archives of ophthalmology 113, 3 (1995), 325--332.
[12]
Ahmed Iqbal, Muhammad Sharif, Mussarat Yasmin, Mudassar Raza, and Shabib Aftab. 2022. Generative adversarial networks and its applications in the biomedical image segmentation: a comprehensive survey. International Journal of Multimedia Information Retrieval 11, 3 (2022), 333--368.
[13]
Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. 2017. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1125--1134.
[14]
Jiwoong J Jeong, Amara Tariq, Tobiloba Adejumo, Hari Trivedi, Judy W Gichoya, and Imon Banerjee. 2022. Systematic review of generative adversarial networks (gans) for medical image classification and segmentation. Journal of Digital Imaging 35, 2 (2022), 137--152.
[15]
SPK Karri, Debjani Chakraborthi, and Jyotirmoy Chatterjee. 2016. Learning layer-specific edges for segmenting retinal layers with large deformations. Biomedical optics express 7, 7 (2016), 2888--2901.
[16]
Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR abs/1412.6980 (2014). https://arxiv.org/abs/1412.6980
[17]
Dara Koozekanani, Kim Boyer, and Cynthia Roberts. 2001. Retinal thickness measurements from optical coherence tomography using a Markov boundary model. IEEE transactions on medical imaging 20, 9 (2001), 900--916.
[18]
Robert Koprowski and Zygmunt Wrobel. 2009. Layers recognition in tomographic eye image based on random contour analysis.
[19]
Andrew Lang, Aaron Carass, Matthew Hauser, Elias S Sotirchos, Peter A Calabresi, Howard S Ying, and Jerry L Prince. 2013. Retinal layer segmentation of macular OCT images using boundary classification. Biomedical optics express 4, 7 (2013), 1133--1152.
[20]
Xiaoming Liu, Jun Cao, Tianyu Fu, Zhifang Pan, Wei Hu, Kai Zhang, and Jun Liu. 2019. Semi-Supervised Automatic Segmentation of Layer and Fluid Region in Retinal Optical Coherence Tomography Images Using Adversarial Learning. IEEE Access 7 (2019), 3046--3061.
[21]
Markus Mayer. 2023. OCTSEG (Optical Coherence Tomography Segmentation and Evaluation GUI). [Software]. https://www.mathworks.com/matlabcentral/fileexchange/66873-octseg-optical-coherence-tomography-segmentation-and-evaluation-gui Retrieved June 11, 2023.
[22]
Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014).
[23]
Zubin Mishra, Anushika Ganegoda, Jane Selicha, Ziyuan Wang, SriniVas R Sadda, and Zhihong Hu. 2020. Automated retinal layer segmentation using graph-based algorithm incorporating deep-learning-derived information. Scientific Reports 10, 1 (2020), 9541.
[24]
Alessio Montuoro, Sebastian M Waldstein, Bianca S Gerendas, Ursula Schmidt-Erfurth, and Hrvoje Bogunović. 2017. Joint retinal layer and fluid segmentation in OCT scans of eyes with severe macular edema using unsupervised representation and auto-context. Biomedical optics express 8, 3 (2017), 1874--1888.
[25]
Souvick Mukherjee, Tharindu De Silva, Peyton Grisso, Henry Wiley, DL Keenan Tiarnan, Alisa T Thavikulwat, Emily Chew, and Catherine Cukras. 2022. Retinal layer segmentation in optical coherence tomography (OCT) using a 3D deep-convolutional regression network for patients with age-related macular degeneration. Biomedical Optics Express 13, 6 (2022), 3195--3210.
[26]
NVIDIA Corporation. 2021. NVIDIA RTX A4000. [Hardware]. https://www.nvidia.com/en-us/design-visualization/rtx-a4000/
[27]
Gwénolé Quellec, Kyungmoo Lee, Martin Dolejsi, Mona K Garvin, Michael D Abramoff, and Milan Sonka. 2010. Three-dimensional analysis of retinal layer texture: identification of fluid-filled regions in SD-OCT of the macula. IEEE transactions on medical imaging 29, 6 (2010), 1321--1330.
[28]
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5--9, 2015, Proceedings, Part III 18. Springer, 234--241.
[29]
Abhay Shah, Michael D Abramoff, and Xiaodong Wu. 2017. Simultaneous multiple surface segmentation using deep learning. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 14, Proceedings. Springer, 3--11.
[30]
Jaemin Son, Sang Jun Park, and Kyu-Hwan Jung. 2019. Towards accurate segmentation of retinal vessels and the optic disc in fundoscopic images with generative adversarial networks. Journal of digital imaging 32, 3 (2019), 499--512.
[31]
Xinge You, Qinmu Peng, Yuan Yuan, Yiu-ming Cheung, and Jiajia Lei. 2011. Segmentation of retinal blood vessels using the radial projection and semi-supervised approach. Pattern recognition 44, 10--11 (2011), 2314--2324.
[32]
Lu Zongqing, Liao Qingmin, and Yang Fan. 2009. A Variational Approach to Automatic Segmentation of RNFL on OCT Data Sets of the Retina. In Proceedings of the 16th IEEE International Conference on Image Processing (Cairo, Egypt) (ICIP'09). IEEE Press, 3309--3312.
Index Terms
- Robust Retinal Layer Segmentation Using OCT B-Scans: A Novel Approach Based on Pix2Pix Generative Adversarial Network
Recommendations
A benchmark study of automated intra-retinal cyst segmentation algorithms using optical coherence tomography B-scans
The different automated OCT intra-retinal cyst segmentation methods are reviewed and comparatively analysed for quantitative and qualitative benchmarking purposes.A modular approach to standardize the existing cyst segmentation methods is presented for ...
Parallel Double Snakes. Application to the segmentation of retinal layers in 2D-OCT for pathological subjects
In order to segment elongated structures, we propose a new approach for integrating an approximate parallelism constraint in deformable models. The proposed Parallel Double Snakes evolve simultaneously two contours, in order to minimize an energy ...
Detection of retinal disorders from OCT images using generative adversarial networks
AbstractRetinal image analysis has opened up a new window for prompt diagnosis and detection of various retinal disorders. Optical Coherence Tomography (OCT) is one of the major diagnostic tools to identify retinal abnormalities related to macular ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2023
626 pages
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 04 October 2023
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Shear Family Foundation
- NIH Core Grant
- Research to prevent blindness
Conference
BCB '23
Sponsor:
BCB '23: 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
September 3 - 6, 2023
TX, Houston, USA
Acceptance Rates
Overall Acceptance Rate 254 of 885 submissions, 29%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 63Total Downloads
- Downloads (Last 12 months)36
- Downloads (Last 6 weeks)4
Reflects downloads up to 14 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in