research-article

Open access

Estimating Glaucomatous Visual Sensitivity from Retinal Thickness with Pattern-Based Regularization and Visualization

Authors:

Hiroki Sugiura,

Siamak Yousefi,

Hiroshi Murata,

Kenji YamanishiAuthors Info & Claims

KDD '18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

Pages 783 - 792

https://doi.org/10.1145/3219819.3219866

Published: 19 July 2018 Publication History

Abstract

Conventionally, glaucoma is diagnosed on the basis of visual field sensitivity (VF). However, the VF test is time-consuming, costly, and noisy. Using retinal thickness (RT) for glaucoma diagnosis is currently desirable. Thus, we propose a new methodology for estimating VF from RT in glaucomatous eyes. The key ideas are to use our new methods of pattern-based regularization (PBR) and pattern-based visualization (PBV) with convolutional neural networks (CNNs). PBR effectively conducts supervised learning of RT-VF relations in combination with unsupervised learning from non-paired VF data. We can thereby avoid overfitting of a CNN to small sized data. PBV visualizes functional correspondence between RT and VF with its nonlinearity preserved. We empirically demonstrate with real datasets that a CNN with PBR achieves the highest estimation accuracy to date and that a CNN with PBV is effective for knowledge discovery in an ophthalmological context.

Supplementary Material

MP4 File (sugiura_glaucomatous_visual_sensitivity.mp4)

Download
361.40 MB

References

[1]

Csilla Ajtony, Zsolt Balla, Szabolcs Somoskeoy, and Balint Kovacs. 2007. Relationship between visual field sensitivity and retinal nerve fiber layer thickness as measured by optical coherence tomography. Investigative ophthalmology &visual science Vol. 48, 1 (2007), 258--263.

[2]

Ryo Asaoka. 2013. The relationship between visual acuity and central visual field sensitivity in advanced glaucoma. British Journal of Ophthalmology (2013), bjophthalmol--2013.

[3]

Gavin C. Cawley and Nicola L. C. Talbot. 2010. On over-fitting in model selection and subsequent selection bias in performance evaluation. Journal of Machine Learning Research Vol. 11, Jul (2010), 2079--2107.

Digital Library

[4]

Olivier Chapelle, Bernhard Schölkopf, and Alexander Zien (Eds.). 2006. Semi-Supervised Learning. MIT Press.

[5]

David DeMers and Garrison W. Cottrell. 1993. Non-linear dimensionality reduction. In Advances in neural information processing systems. 580--587.

Digital Library

[6]

Mariko Eura. 2014. orrespondence Between Visual Field Test Results and GCL+IPL Thickness in the Maculae of Glaucomatous Eyes. Ph.D. Thesis (2014).

[7]

Stuart K. Gardiner, Steven L. Mansberger, and Shaban Demirel. 2017. Detection of Functional Change Using Cluster Trend Analysis in Glaucoma. Investigative ophthalmology &visual science Vol. 58, 6 (2017), BIO180--BIO190.

[8]

Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research), Yee Whye Teh and Mike Titterington (Eds.), Vol. Vol. 9. 249--256.

[9]

Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. The MIT Press.

Digital Library

[10]

Motohide Higaki, Kai Morino, Hiroshi Murata, Ryo Asaoka, and Kenji Yamanishi. 2016. Predicting Glaucoma Visual Field Loss by Hierarchically Aggregating Clustering-based Predictors. arXiv preprint arXiv:1603.07094 (2016).

[11]

Geoffrey E. Hinton and Ruslan R. Salakhutdinov. 2006. Reducing the dimensionality of data with neural networks. science Vol. 313, 5786 (2006), 504--507.

[12]

CATHARINA HOLMIN and CET Krakau. 1982. Regression analysis of the central visual field in chronic glaucoma cases. Acta ophthalmologica Vol. 60, 2 (1982), 267--274.

[13]

Donald C. Hood. 2016. Improving our understanding, and detection, of glaucomatous damage: An approach based upon optical coherence tomography (OCT). Progress in retinal and eye research (2016).

[14]

Donald C. Hood and Randy H. Kardon. 2007. A framework for comparing structural and functional measures of glaucomatous damage. Progress in retinal and eye research Vol. 26, 6 (2007), 688--710.

[15]

David Huang, Eric A. Swanson, Charles P. Lin, Joel S. Schuman, William G. Stinson, Warren Chang, Michael R. Hee, Thomas Flotte, Kenton Gregory, Carmen A. Puliafito, et al. 1991. Optical coherence tomography. science Vol. 254, 5035 (1991), 1178--1181.

[16]

Akiyasu Kanamori, Makoto Nakamura, Michael F. T. Escano, Ryu Seya, Hidetaka Maeda, and Akira Negi. 2003. Evaluation of the glaucomatous damage on retinal nerve fiber layer thickness measured by optical coherence tomography. American journal of ophthalmology Vol. 135, 4 (2003), 513--520.

[17]

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS'12). Curran Associates Inc., USA, 1097--1105.

Digital Library

[18]

Daniel D. Lee and H. Sebastian Seung. 2001. Algorithms for non-negative matrix factorization. In Advances in neural information processing systems. 556--562.

[19]

Zenghan Liang, Ryota Tomioka, Hiroshi Murata, Ryo Asaoka, and Kenji Yamanishi. 2013. Quantitative prediction of glaucomatous visual field loss from few measurements Data Mining (ICDM), 2013 IEEE 13th International Conference on. IEEE, 1121--1126.

[20]

Shigeru Maya, Kai Morino, Hiroshi Murata, Ryo Asaoka, and Kenji Yamanishi. 2015. Discovery of Glaucoma Progressive Patterns Using Hierarchical MDL-Based Clustering Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 1979--1988.

Digital Library

[21]

Shigeru Maya, Kai Morino, and Kenji Yamanishi. 2014. Predicting glaucoma progression using multi-task learning with heterogeneous features Big Data (Big Data), 2014 IEEE International Conference on. IEEE, 261--270.

[22]

B. N. Noureddin, D. Poinoosawmy, F. W. Fietzke, and R. A. Hitchings. 1991. Regression analysis of visual field progression in low tension glaucoma. British journal of ophthalmology Vol. 75, 8 (1991), 493--495.

[23]

Ning Qian. 1999. On the momentum term in gradient descent learning algorithms. Neural networks Vol. 12, 1 (1999), 145--151.

Digital Library

[24]

Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. 2015. Imagenet large scale visual recognition challenge. International Journal of Computer Vision Vol. 115, 3 (2015), 211--252.

Digital Library

[25]

T. M. Shaarawy, M. B. Sherwood, R. A. Hitchings, and J. G. Crowston. 2009. Glaucoma: Medical Diagnosis and Therapy, Vol. 1. Vol. 1. Elsevier.

[26]

Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013).

[27]

Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).

[28]

Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, et al. 2015. Going Deeper with Convolutions. In CVPR.

[29]

Kyosuke Tomoda, Kai Morino, Hiroshi Murata, Ryo Asaoka, and Kenji Yamanishi. 2016. Predicting Glaucomatous Progression with Piecewise Regression Model from Heterogeneous Medical Data. HEALTHINF Vol. 2016 (2016).

[30]

Toshimitsu Uesaka, Kai Morino, Hiroki Sugiura, Taichi Kiwaki, Hiroshi Murata, Ryo Asaoka, and Kenji Yamanishi. 2017. Multi-view Learning over Retinal Thickness and Visual Sensitivity on Glaucomatous Eyes. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2041--2050.

Digital Library

[31]

Jason Yosinski, Jeff Clune, Yoshua Bengio, and Hod Lipson. 2014. How transferable are features in deep neural networks? Advances in neural information processing systems. 3320--3328.

Digital Library

[32]

Siamak Yousefi, Michael H. Goldbaum, Madhusudhanan Balasubramanian, Tzyy-Ping Jung, Robert N. Weinreb, Felipe A. Medeiros, Linda M. Zangwill, Jeffrey M. Liebmann, Christopher A. Girkin, and Christopher Bowd. 2014. Glaucoma progression detection using structural retinal nerve fiber layer measurements and functional visual field points. IEEE Transactions on Biomedical Engineering Vol. 61, 4 (2014), 1143--1154.

[33]

Xiaojin Zhu. 2006. Semi-supervised learning literature survey. Computer Science, University of Wisconsin-Madison Vol. 2, 3 (2006), 4.

Cited By

Deepshikha Megha MVishnu K(2023)A review on glaucoma detection using deep learning algorithmsi-manager’s Journal on Image Processing10.26634/jip.10.1.1938210:1(29)Online publication date: 2023
https://doi.org/10.26634/jip.10.1.19382
Pham QHan JPark DShin J(2023)Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma PatientsIEEE Access10.1109/ACCESS.2023.324806511(19049-19058)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3248065
Mariottoni EMedeiros FCosta V(2022)A review of deep learning in structure and function in glaucomaModeling and Artificial Intelligence in Ophthalmology10.35119/maio.v4i1.1254:1Online publication date: 27-Oct-2022
https://doi.org/10.35119/maio.v4i1.125
Show More Cited By

Index Terms

Estimating Glaucomatous Visual Sensitivity from Retinal Thickness with Pattern-Based Regularization and Visualization
1. Applied computing
  1. Life and medical sciences
    1. Health informatics
2. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Factorization methods
        Non-negative matrix factorization
        Principal component analysis

Recommendations

Multi-view Learning over Retinal Thickness and Visual Sensitivity on Glaucomatous Eyes
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Dense measurements of visual-field, which is necessary to detect glaucoma, is known as very costly and labor intensive. Recently, measurement of retinal-thickness can be less costly than measurement of visual-field. Thus, it is sincerely desired that ...
A framework for detecting glaucomatous progression in the optic nerve head of an eye using proper orthogonal decomposition
Special section on computational intelligence in medical systems

Glaucoma is the second leading cause of blindness worldwide. Often, the optic nerve head (ONH) glaucomatous damage and ONH changes occur prior to visual field loss and are observable in vivo. Thus, digital image analysis is a promising choice for ...
Optic disc and optic cup segmentation from retinal images using hybrid approach
Highlights
- Glaucoma is an eye disease caused due to raise in the intraocular pressure of eye.
Abstract
In the present scenario, humans are surrounded by numerous diseases which affect their lifestyles. One such condition is glaucoma which originates due to sudden stress in the eye, generally termed as intraocular pressure culminating in ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

KDD '18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

July 2018

2925 pages

ISBN:9781450355520

DOI:10.1145/3219819

General Chairs:
Yike Guo
Imperial College London
,
Faisal Farooq
IBM

Copyright © 2018 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 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]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 July 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

JST CREST, Japan
JSPS KAKENHI, Japan

Conference

KDD '18

Sponsor:

KDD '18: The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

August 19 - 23, 2018

London, United Kingdom

Acceptance Rates

KDD '18 Paper Acceptance Rate 107 of 983 submissions, 11%;

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

15
Total Citations
View Citations
7,125
Total Downloads

Downloads (Last 12 months)6,384
Downloads (Last 6 weeks)22

Reflects downloads up to 10 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Deepshikha Megha MVishnu K(2023)A review on glaucoma detection using deep learning algorithmsi-manager’s Journal on Image Processing10.26634/jip.10.1.1938210:1(29)Online publication date: 2023
https://doi.org/10.26634/jip.10.1.19382
Pham QHan JPark DShin J(2023)Multimodal Deep Learning Model of Predicting Future Visual Field for Glaucoma PatientsIEEE Access10.1109/ACCESS.2023.324806511(19049-19058)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3248065
Mariottoni EMedeiros FCosta V(2022)A review of deep learning in structure and function in glaucomaModeling and Artificial Intelligence in Ophthalmology10.35119/maio.v4i1.1254:1Online publication date: 27-Oct-2022
https://doi.org/10.35119/maio.v4i1.125
Tong JAlonso‐Caneiro DKalloniatis MZangerl B(2022)Prediction of visual field defects from macular optical coherence tomography in glaucoma using cluster analysisOphthalmic and Physiological Optics10.1111/opo.1299742:5(948-964)Online publication date: 22-May-2022
https://doi.org/10.1111/opo.12997
Saravanan VSamuel RKrishnamoorthy SManickam A(2022)Deep learning assisted convolutional auto-encoders framework for glaucoma detection and anterior visual pathway recognition from retinal fundus imagesJournal of Ambient Intelligence and Humanized Computing10.1007/s12652-021-02928-0Online publication date: 26-Jan-2022
https://doi.org/10.1007/s12652-021-02928-0
Huang XSun JMajoor JVermeer KLemij HElze TWang MBoland MPasquale LMohammadzadeh VNouri-Mahdavi KJohnson CYousefi S(2021)Estimating the Severity of Visual Field Damage From Retinal Nerve Fiber Layer Thickness Measurements With Artificial IntelligenceTranslational Vision Science & Technology10.1167/tvst.10.9.1610:9(16)Online publication date: 16-Aug-2021
https://doi.org/10.1167/tvst.10.9.16
Hashimoto YKiwaki TSugiura HAsano SMurata HFujino YMatsuura MMiki AMori KIkeda YKanamoto TYamagami JInoue KTanito MYamanishi KAsaoka R(2021)Predicting 10-2 Visual Field From Optical Coherence Tomography in Glaucoma Using Deep Learning Corrected With 24-2/30-2 Visual FieldTranslational Vision Science & Technology10.1167/tvst.10.13.2810:13(28)Online publication date: 23-Nov-2021
https://doi.org/10.1167/tvst.10.13.28
Datta SMariottoni EDov DJammal ACarin LMedeiros F(2021)RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structureScientific Reports10.1038/s41598-021-91493-911:1Online publication date: 15-Jun-2021
https://doi.org/10.1038/s41598-021-91493-9
Lavric APopa VTakahashi HHazarbassanov RYousefi S(2021)Association between visual field damage and corneal structural parametersScientific Reports10.1038/s41598-021-90298-011:1Online publication date: 24-May-2021
https://doi.org/10.1038/s41598-021-90298-0
Christopher MBowd CProudfoot JBelghith AGoldbaum MRezapour JFazio MGirkin CDe Moraes GLiebmann JWeinreb RZangwill L(2021)Deep Learning Estimation of 10-2 and 24-2 Visual Field Metrics based on Thickness Maps from Macula Optical Coherence TomographyOphthalmology10.1016/j.ophtha.2021.04.022Online publication date: Apr-2021
https://doi.org/10.1016/j.ophtha.2021.04.022
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents