Glaucoma Monitoring Using Manifold Learning and Unsupervised Clustering

Siamak Yousefi, Tobias Elze, Louis R. Pasquale, Michael Boland

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

Abstract

We developed an artificial-intelligence-enabled software for monitoring eyes with glaucoma using manifold learning and unsupervised clustering. A total of 31,591 visual fields (VF) measurements from 8,077 subjects were acquired using the Humphrey Field Analyzers instrument. The two locations closest to the blind spot were excluded from each VF. The number of remaining VFs were 13,231 with 52 VF test locations (features). We first applied principal component analysis (PCA) to linearly reduce the number of dimensions from 52 to four significant principal components. We then developed a manifold learning algorithm to identify VFs with similar patterns of VF loss. Manifold learning preserved the local characteristics of the input principal components and nonlinearly reduced the dimensions further. Finally, we developed an unsupervised density-based clustering to identify clusters at different stages of glaucoma as well as different patterns of VF loss. We evaluated the quality of learning using both subjective visualization of clusters and objective validation using global VF parameters including mean deviation (MD) and pattern standard deviation (PSD). The proposed tool could be highly useful in clinical practice and glaucoma research for monitoring and staging glaucoma.

Original languageEnglish (US)
Title of host publication2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018
PublisherIEEE Computer Society
ISBN (Electronic)9781728101255
DOIs
StatePublished - Feb 4 2019
Event2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018 - Auckland, New Zealand
Duration: Nov 19 2018Nov 21 2018

Publication series

NameInternational Conference Image and Vision Computing New Zealand
Volume2018-November
ISSN (Print)2151-2191
ISSN (Electronic)2151-2205

Conference

Conference2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018
CountryNew Zealand
CityAuckland
Period11/19/1811/21/18

Fingerprint

Monitoring
Principal component analysis
Learning algorithms
Artificial intelligence
Visualization

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Yousefi, S., Elze, T., Pasquale, L. R., & Boland, M. (2019). Glaucoma Monitoring Using Manifold Learning and Unsupervised Clustering. In 2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018 [8634733] (International Conference Image and Vision Computing New Zealand; Vol. 2018-November). IEEE Computer Society. https://doi.org/10.1109/IVCNZ.2018.8634733

Glaucoma Monitoring Using Manifold Learning and Unsupervised Clustering. / Yousefi, Siamak; Elze, Tobias; Pasquale, Louis R.; Boland, Michael.

2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018. IEEE Computer Society, 2019. 8634733 (International Conference Image and Vision Computing New Zealand; Vol. 2018-November).

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

Yousefi, S, Elze, T, Pasquale, LR & Boland, M 2019, Glaucoma Monitoring Using Manifold Learning and Unsupervised Clustering. in 2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018., 8634733, International Conference Image and Vision Computing New Zealand, vol. 2018-November, IEEE Computer Society, 2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018, Auckland, New Zealand, 11/19/18. https://doi.org/10.1109/IVCNZ.2018.8634733
Yousefi S, Elze T, Pasquale LR, Boland M. Glaucoma Monitoring Using Manifold Learning and Unsupervised Clustering. In 2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018. IEEE Computer Society. 2019. 8634733. (International Conference Image and Vision Computing New Zealand). https://doi.org/10.1109/IVCNZ.2018.8634733
Yousefi, Siamak ; Elze, Tobias ; Pasquale, Louis R. ; Boland, Michael. / Glaucoma Monitoring Using Manifold Learning and Unsupervised Clustering. 2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018. IEEE Computer Society, 2019. (International Conference Image and Vision Computing New Zealand).
@inproceedings{8b8019ec2c894165a3f6a2e27fdb993c,
title = "Glaucoma Monitoring Using Manifold Learning and Unsupervised Clustering",
abstract = "We developed an artificial-intelligence-enabled software for monitoring eyes with glaucoma using manifold learning and unsupervised clustering. A total of 31,591 visual fields (VF) measurements from 8,077 subjects were acquired using the Humphrey Field Analyzers instrument. The two locations closest to the blind spot were excluded from each VF. The number of remaining VFs were 13,231 with 52 VF test locations (features). We first applied principal component analysis (PCA) to linearly reduce the number of dimensions from 52 to four significant principal components. We then developed a manifold learning algorithm to identify VFs with similar patterns of VF loss. Manifold learning preserved the local characteristics of the input principal components and nonlinearly reduced the dimensions further. Finally, we developed an unsupervised density-based clustering to identify clusters at different stages of glaucoma as well as different patterns of VF loss. We evaluated the quality of learning using both subjective visualization of clusters and objective validation using global VF parameters including mean deviation (MD) and pattern standard deviation (PSD). The proposed tool could be highly useful in clinical practice and glaucoma research for monitoring and staging glaucoma.",
author = "Siamak Yousefi and Tobias Elze and Pasquale, {Louis R.} and Michael Boland",
year = "2019",
month = "2",
day = "4",
doi = "10.1109/IVCNZ.2018.8634733",
language = "English (US)",
series = "International Conference Image and Vision Computing New Zealand",
publisher = "IEEE Computer Society",
booktitle = "2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018",
address = "United States",

}

TY - GEN

T1 - Glaucoma Monitoring Using Manifold Learning and Unsupervised Clustering

AU - Yousefi, Siamak

AU - Elze, Tobias

AU - Pasquale, Louis R.

AU - Boland, Michael

PY - 2019/2/4

Y1 - 2019/2/4

N2 - We developed an artificial-intelligence-enabled software for monitoring eyes with glaucoma using manifold learning and unsupervised clustering. A total of 31,591 visual fields (VF) measurements from 8,077 subjects were acquired using the Humphrey Field Analyzers instrument. The two locations closest to the blind spot were excluded from each VF. The number of remaining VFs were 13,231 with 52 VF test locations (features). We first applied principal component analysis (PCA) to linearly reduce the number of dimensions from 52 to four significant principal components. We then developed a manifold learning algorithm to identify VFs with similar patterns of VF loss. Manifold learning preserved the local characteristics of the input principal components and nonlinearly reduced the dimensions further. Finally, we developed an unsupervised density-based clustering to identify clusters at different stages of glaucoma as well as different patterns of VF loss. We evaluated the quality of learning using both subjective visualization of clusters and objective validation using global VF parameters including mean deviation (MD) and pattern standard deviation (PSD). The proposed tool could be highly useful in clinical practice and glaucoma research for monitoring and staging glaucoma.

AB - We developed an artificial-intelligence-enabled software for monitoring eyes with glaucoma using manifold learning and unsupervised clustering. A total of 31,591 visual fields (VF) measurements from 8,077 subjects were acquired using the Humphrey Field Analyzers instrument. The two locations closest to the blind spot were excluded from each VF. The number of remaining VFs were 13,231 with 52 VF test locations (features). We first applied principal component analysis (PCA) to linearly reduce the number of dimensions from 52 to four significant principal components. We then developed a manifold learning algorithm to identify VFs with similar patterns of VF loss. Manifold learning preserved the local characteristics of the input principal components and nonlinearly reduced the dimensions further. Finally, we developed an unsupervised density-based clustering to identify clusters at different stages of glaucoma as well as different patterns of VF loss. We evaluated the quality of learning using both subjective visualization of clusters and objective validation using global VF parameters including mean deviation (MD) and pattern standard deviation (PSD). The proposed tool could be highly useful in clinical practice and glaucoma research for monitoring and staging glaucoma.

UR - http://www.scopus.com/inward/record.url?scp=85062808534&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062808534&partnerID=8YFLogxK

U2 - 10.1109/IVCNZ.2018.8634733

DO - 10.1109/IVCNZ.2018.8634733

M3 - Conference contribution

T3 - International Conference Image and Vision Computing New Zealand

BT - 2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018

PB - IEEE Computer Society

ER -