Estimating glaucomatous visual sensitivity from retinal thickness with pattern-based regularization and visualization

Hiroki Sugiura, Hiroshi Murata, Taichi Kiwaki, Ryo Asaoka, Siamak Yousefi, Kenji Yamanishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationKDD 2018 - Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages783-792
Number of pages10
ISBN (Print)9781450355520
DOIs
StatePublished - Jul 19 2018
Event24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2018 - London, United Kingdom
Duration: Aug 19 2018Aug 23 2018

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Other

Other24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2018
CountryUnited Kingdom
CityLondon
Period8/19/188/23/18

Fingerprint

Visualization
Neural networks
Unsupervised learning
Supervised learning
Data mining

All Science Journal Classification (ASJC) codes

  • Software
  • Information Systems

Cite this

Sugiura, H., Murata, H., Kiwaki, T., Asaoka, R., Yousefi, S., & Yamanishi, K. (2018). Estimating glaucomatous visual sensitivity from retinal thickness with pattern-based regularization and visualization. In KDD 2018 - Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 783-792). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery. https://doi.org/10.1145/3219819.3219866

Estimating glaucomatous visual sensitivity from retinal thickness with pattern-based regularization and visualization. / Sugiura, Hiroki; Murata, Hiroshi; Kiwaki, Taichi; Asaoka, Ryo; Yousefi, Siamak; Yamanishi, Kenji.

KDD 2018 - Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2018. p. 783-792 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sugiura, H, Murata, H, Kiwaki, T, Asaoka, R, Yousefi, S & Yamanishi, K 2018, Estimating glaucomatous visual sensitivity from retinal thickness with pattern-based regularization and visualization. in KDD 2018 - Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, pp. 783-792, 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2018, London, United Kingdom, 8/19/18. https://doi.org/10.1145/3219819.3219866
Sugiura H, Murata H, Kiwaki T, Asaoka R, Yousefi S, Yamanishi K. Estimating glaucomatous visual sensitivity from retinal thickness with pattern-based regularization and visualization. In KDD 2018 - Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery. 2018. p. 783-792. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). https://doi.org/10.1145/3219819.3219866
Sugiura, Hiroki ; Murata, Hiroshi ; Kiwaki, Taichi ; Asaoka, Ryo ; Yousefi, Siamak ; Yamanishi, Kenji. / Estimating glaucomatous visual sensitivity from retinal thickness with pattern-based regularization and visualization. KDD 2018 - Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2018. pp. 783-792 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).
@inproceedings{e5737020314942f389b332bde8ec6b7f,
title = "Estimating glaucomatous visual sensitivity from retinal thickness with pattern-based regularization and visualization",
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.",
author = "Hiroki Sugiura and Hiroshi Murata and Taichi Kiwaki and Ryo Asaoka and Siamak Yousefi and Kenji Yamanishi",
year = "2018",
month = "7",
day = "19",
doi = "10.1145/3219819.3219866",
language = "English (US)",
isbn = "9781450355520",
series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",
pages = "783--792",
booktitle = "KDD 2018 - Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

}

TY - GEN

T1 - Estimating glaucomatous visual sensitivity from retinal thickness with pattern-based regularization and visualization

AU - Sugiura, Hiroki

AU - Murata, Hiroshi

AU - Kiwaki, Taichi

AU - Asaoka, Ryo

AU - Yousefi, Siamak

AU - Yamanishi, Kenji

PY - 2018/7/19

Y1 - 2018/7/19

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85051534041&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051534041&partnerID=8YFLogxK

U2 - 10.1145/3219819.3219866

DO - 10.1145/3219819.3219866

M3 - Conference contribution

SN - 9781450355520

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 783

EP - 792

BT - KDD 2018 - Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

ER -