skip to main content
10.1145/3417519.3417560acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicbipConference Proceedingsconference-collections
research-article

BG-CNN: A Boundary Guided Convolutional Neural Network for Corneal Layer Segmentation from Optical Coherence Tomography

Published: 25 September 2020 Publication History

Abstract

Precise segmentation of corneal layers depicted on optical coherence tomography (OCT) images plays an important role in detecting corneal diseases, such as keratoconus and dry eye. In this study, we present a boundary guided convolutional neural network (BG-CNN) to extract different corneal layers. The developed network uses three convolutional blocks to construct two network modules derived from the classical U-Net network. This network was trained based on a dataset consisting of 1712 OCT images. The segmentation results demonstrated the developed network achieved an average dice similarity coefficient (DSC) of 0.9599 and an interFiguresection over union (IOU) of 0.9253 on an independent testing set from our dataset, and it outperformed some available segmentation networks.

References

[1]
Delmonte, D., Kim, T. 2011. Anatomy and physiology of the cornea, Journal of cataract & refractive surgery, 37(3) (Mar, 2011), 0-598, 2011. DOI= https://doi.org/10.1016/j.jcrs.2010.12.037
[2]
Liu, A., Brown, D., Conn, R., McNabb, P., Pardue, M., Kuo, A. 2020. Topography and pachymetry maps for mouse corneas using optical coherence tomography, Experimental Eye Research (Jan, 2020), 190:107868. DOI= https://doi.org/10.1016/j.exer.2019.107868
[3]
Wang, J., Shousha, M., Perez, V., Karp, C., Yoo, S., Shen, M., Cui, L., Hurmeric, V., Du, C., Zhu, D., Chen, Q., Li, M. 2011. Ultra-high resolution optical coherence tomography for imaging the anterior segment of the eye, Ophthalmic Surg Lasers Imaging, 42 (Jan, 2011), S15-S27. DOI=https://doi.org/10.1016/j.jtos.2013.11.001
[4]
Shousha, M., Perez, V., Canto, A., Vaddavalli, P., Sayyad, F., Cabot, F., Feuer, W., Wang, J., Yoo, S. 2014. The use of Bowman's layer vertical topographic thickness map in the diagnosis of keratoconus, Ophthalmology, 121 (May, 2014), 988--993. DOI=https://doi.org/10.1016/j.ophtha.2013.11.034
[5]
Roongpoovapatr, V., Elsawy, A., Wen, D., Kanokkantapong, J., Ahmed, I., Syed, Z., Mottaleb, M., Yoo, S., Shousha, M. 2018. Three-dimensional Bowmans microlayer optical coherence tomography for the diagnosis of subclinical keratoconus, Invest Ophthalmol Vis Sci., 59 (Jul, 2018), 5742.
[6]
Rabbani, H., Kafieh, R., Amini, Z. 2016. Optical Coherence Tomography Image Analysis, Wiley Encyclopdia of Electrical and Electronics Engineering, John Wiley & Sons, Inc (Aug, 2016). DOI=https://doi.org/10.1002/047134608X.W8315
[7]
Shousha, M., Karp, C., Perez, V., Hoffmann, R., Ventura, R., Chang, V., Dubovy, S., Wang, J. 2011. Diagnosis and management of conjunctival and corneal intraepithelial neoplasia using ultra highresolution optical coherence tomography, Ophthalmology, 118 (Aug, 2011), 1531--1537. DOI=https://doi.org/10.1016/j.ophtha.2011.01.005
[8]
Hoffmann, R., Shousha, M., Karp, C., Awdeh, R., Kieval, J., Dubovy, S., Perez, L., Chang, V., Yoo, S., Wang, J. 2009. Optical biopsy of corneal-conjunctival intraepithelial neoplasia using ultra-high resolution optical coherence tomography. Invest Ophthalmol Vis Sci., 50 (Apr, 2009), 5795.
[9]
Kuruvilla, J., Sukumaran, D., Sankar, A., Joy, S. 2016. A review on image processing and image segmentation, 2016 International Conference on Data Mining and Advanced Computing (SAPIENCE) (Dec, 2016), 198--203. DOI=https://doi.org/10.1109/SAPIENCE.2016.7684170
[10]
Chen, C., Qin, C., Qiu, H., Tarroni, G., Duan, J., Bai, W., Rueckert, D. 2019. Deep learning for cardiac image segmentation: A review, arXiv:1911.03723, 2019
[11]
Geroge, N., Jiji, C. 2019. Two stage contour evolution for automatic segmentation of choroid and cornea in OCT images, Biocybernetics and biomedical Engineering, 39 (Jul, 2019), 686--696. DOI=https://doi.org/10.1016/j.bbe.2019.05.012
[12]
LaRocca, F., Chiu, S., McNabb, R., Kuo, A., Izatt, J., Farsiu, S. 2011. Robust automatic segmentation of corneal layer boundaries in SDOCT images using graph theory and dynamic programming, Biomed Opt Express, 1524(2) (Jun, 2011). DOI=https://doi.org/10.1364/BOE.2.001524
[13]
Eichel, J., Mishra, A., Clausi, D., Fieguth, P., Bizheva, K. 2009. A novel algorithm for extraction of the layers of the cornea. Proc 2009 Can Conf Comput Robot Vision (May, 2009), 313--320. DOI=https://doi.org/10.1109/CRV.2009.22
[14]
Elsawy, A., Mottaleb, M., Sayed, I., Wen, D., Roongpoovapatr, V., Eleiwa, T., Sayed, A., Raheem, M., Gameiro, G., Shousha, M. 2019. Automatic Segmentation of Corneal Microlayers on Optical Coherence Tomography Images, Translational vision science & technology, 8(3) (Jun, 2019), 39. DOI=https://doi.org/10.1167/tvst.8.3.39
[15]
Wang, L., Chen, G., Shi, D., Chang, Y., Chan, S., Pu, J., Yang, X. 2018. Active contours driven by edge entropy fitting energy for image segmentation, Signal Processing, 149 (Mar, 2018), 27--35. DOI= https://doi.org/10.1016/j.sigpro.2018.02.025
[16]
Wang, L., Zhang, L., Yang, X., Yi, P., Chen, H. 2020. Level set based segmentation using local fitted images and inhomogeneity entropy, Signal Processing, 167(107297) (Feb, 2020). DOI=https://doi.org/10.1016/j.sigpro.2019.107297
[17]
Litjens, G., Kooi, T., Bejnordi, B., Setio, A., Ciompi, F., Ghafoorian, M., Laak, J., Ginneken, B., Sanchez, C. 2017. A survey on deep learning in medical image analysis, Medical Image Analysis 42 (Dec, 2017), 60--68. DOI=https://doi.org/10.1016/j.media.2017.07.005
[18]
Wang, L., Liu, H., Zhang, J., Chen, H., Pu, J. 2019. Automated segmentation of the optic disc using the deep learning, SPIE Medical Imaging 2019: Image Processing (Mar, 2019). DOI= https://doi.org/10.1117/12.2510372
[19]
Wang, L., Liu, H., Lu, Y., Chen, H., Zhang, J., Pu, J. 2019. A coarse-to-fine deep learning framework for optic disc segmentation in fundus images, Biomedical Signal Processing and Control, 51 (Jan, 2019), 82--89. DOI= https://doi.org/10.1016/j.bspc.2019.01.022
[20]
Ronneberger, O., Fischer, P. Brox, T. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation, arXiv:1505.04597v1, 2015.
[21]
Fu, H., Cheng, J., Xu, Y., Wong, D., Liu, J., Cao, X. 2018. Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation, IEEE Transactions on Medical Imaging, 37(7) (Jul, 2018), 1597--1605. DOI=https://doi.org/10.1109/TMI.2018.2791488
[22]
Wang, S., Yu, L., Yang, X., Fu, C., Heng, P. 2019. Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation, IEEE Transactions on Medical Imaging, 38(11) (Nov, 2019), 2485--2495. DOI=https://doi.org/10.1109/TMI.2019.2899910
[23]
Liu, H., Wang, L., Nan, Y., Jin, F., Wang, Q., Pu, J. 2019. SDFN:Segmentation-based deep fusion network for thoracic disease classification in chest X-ray images, Computerized Medical Imaging and Graphics, 75 (Jul, 2019), 66--73. DOI=https://doi.org/10.1016/j.compmedimag.2019.05.005
[24]
Wang, L., Zhu, J., Sheng, M., Cribb, A., Zhu, S., Pu, J. 2018. Simultaneous segmentation and bias field estimation using local fitted images, Pattern Recognition, 74 (Sep, 2018), 145--155. DOI= https://doi.org/10.1016/j.patcog.2017.08.031
[25]
Wang, L., Chang, Y., Wang, H., Wu, Z., Pu, J., Yang, X. 2017. An active contour model based on local fitted images for image segmentation, Information Sciences, 418 (Jul, 2017), 61--73. DOI= https://doi.org/10.1016/j.ins.2017.06.042.

Cited By

View all
  • (2024)Expansive Receptive Field and Local Feature Extraction Network: Advancing Multiscale Feature Fusion for Breast Fibroadenoma Segmentation in SonographyJournal of Imaging Informatics in Medicine10.1007/s10278-024-01142-637:6(2810-2824)Online publication date: 31-May-2024
  • (2023)Automated segmentation of palpebral fissures from eye videography using a texture fusion neural networkBiomedical Signal Processing and Control10.1016/j.bspc.2023.10482085(104820)Online publication date: Aug-2023
  • (2022)EE-Net: An edge-enhanced deep learning network for jointly identifying corneal micro-layers from optical coherence tomographyBiomedical Signal Processing and Control10.1016/j.bspc.2021.10321371(103213)Online publication date: Jan-2022

Index Terms

  1. BG-CNN: A Boundary Guided Convolutional Neural Network for Corneal Layer Segmentation from Optical Coherence Tomography

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Other conferences
      ICBIP '20: Proceedings of the 5th International Conference on Biomedical Signal and Image Processing
      August 2020
      99 pages
      ISBN:9781450387767
      DOI:10.1145/3417519
      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 ACM 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]

      In-Cooperation

      • Sichuan University

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 25 September 2020

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. Convolutional neural networks
      2. Corneal layers
      3. Image segmentation
      4. OCT
      5. U-Net

      Qualifiers

      • Research-article
      • Research
      • Refereed limited

      Funding Sources

      • Wenzhou Science & Technology Bureau
      • Jiangsu Natural Science Foundation

      Conference

      ICBIP '20

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)9
      • Downloads (Last 6 weeks)1
      Reflects downloads up to 20 Jan 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2024)Expansive Receptive Field and Local Feature Extraction Network: Advancing Multiscale Feature Fusion for Breast Fibroadenoma Segmentation in SonographyJournal of Imaging Informatics in Medicine10.1007/s10278-024-01142-637:6(2810-2824)Online publication date: 31-May-2024
      • (2023)Automated segmentation of palpebral fissures from eye videography using a texture fusion neural networkBiomedical Signal Processing and Control10.1016/j.bspc.2023.10482085(104820)Online publication date: Aug-2023
      • (2022)EE-Net: An edge-enhanced deep learning network for jointly identifying corneal micro-layers from optical coherence tomographyBiomedical Signal Processing and Control10.1016/j.bspc.2021.10321371(103213)Online publication date: Jan-2022

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media