Keratoconus severity identification using unsupervised machine learning

Siamak Yousefi, Ebrahim Yousefi, Hidenori Takahashi, Takahiko Hayashi, Hironobu Tampo, Satoru Inoda, Yusuke Arai, Penny Asbell

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We developed an unsupervised machine learning algorithm and applied it to big corneal parameters to identify and monitor keratoconus stages. A big dataset of corneal swept source optical coherence tomography (OCT) images of 12,242 eyes acquired from SS-1000 CASIA OCT Imaging Systems in multiple centers across Japan was assembled. A total of 3,156 eyes with valid Ectasia Status Index (ESI) between zero and 100% were selected for the downstream analysis. Four hundred and twenty corneal topography, elevation, and pachymetry parameters (excluding ESI Keratoconus indices) were selected. The algorithm included three major steps. 1) Principal component analysis (PCA) was used to linearly reduce the dimensionality of the input data from 420 to eight significant principal components. 2) Manifold learning was used to further reducing the selected principal components nonlinearly to two eigen-parameters. 3) Finally, a density-based clustering was applied to the eigen-parameters to identify eyes with keratoconus. Visualization of clusters in 2-D space was used to validate the quality of learning subjectively and ESI was used to assess the accuracy of the identified clusters objectively. The proposed method identified four clusters; I: a cluster composed of mostly normal eyes (224 eyes with ESI equal to zero, 23 eyes with ESI between five and 29, and nine eyes with ESI greater than 29), II: a cluster composed of mostly healthy eyes and eyes with forme fruste keratoconus (1772 eyes with ESI equal to zero, 698 eyes with ESI between five and 29, and 117 eyes with ESI greater than 29), III: a cluster composed of mostly eyes with mild keratoconus stage (184 eyes with ESI greater than 29, 74 eyes with ESI between five and 29, and 6 eyes with ESI equal to zero), and IV: a cluster composed of eyes with mostly advanced keratoconus stage (80 eyes had ESI greater than 29 and 1 eye had ESI between five and 29). We found that keratoconus status and severity can be well identified using unsupervised machine learning algorithms along with linear and non-linear corneal data transformation. The proposed method can better identify and visualize the keratoconus stages.

Original languageEnglish (US)
Article numbere0205998
JournalPloS one
Volume13
Issue number11
DOIs
StatePublished - Jan 1 2018

Fingerprint

Keratoconus
artificial intelligence
Optical tomography
Pathologic Dilatations
Learning algorithms
Learning systems
Identification (control systems)
eyes
Imaging systems
Principal component analysis
Topography
Visualization
Unsupervised Machine Learning
tomography
Optical Coherence Tomography
learning
Corneal Pachymetry
Learning
Corneal Topography

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Keratoconus severity identification using unsupervised machine learning. / Yousefi, Siamak; Yousefi, Ebrahim; Takahashi, Hidenori; Hayashi, Takahiko; Tampo, Hironobu; Inoda, Satoru; Arai, Yusuke; Asbell, Penny.

In: PloS one, Vol. 13, No. 11, e0205998, 01.01.2018.

Research output: Contribution to journalArticle

Yousefi, S, Yousefi, E, Takahashi, H, Hayashi, T, Tampo, H, Inoda, S, Arai, Y & Asbell, P 2018, 'Keratoconus severity identification using unsupervised machine learning', PloS one, vol. 13, no. 11, e0205998. https://doi.org/10.1371/journal.pone.0205998
Yousefi S, Yousefi E, Takahashi H, Hayashi T, Tampo H, Inoda S et al. Keratoconus severity identification using unsupervised machine learning. PloS one. 2018 Jan 1;13(11). e0205998. https://doi.org/10.1371/journal.pone.0205998
Yousefi, Siamak ; Yousefi, Ebrahim ; Takahashi, Hidenori ; Hayashi, Takahiko ; Tampo, Hironobu ; Inoda, Satoru ; Arai, Yusuke ; Asbell, Penny. / Keratoconus severity identification using unsupervised machine learning. In: PloS one. 2018 ; Vol. 13, No. 11.
@article{d130f41e67c1436c95f60939082e83f7,
title = "Keratoconus severity identification using unsupervised machine learning",
abstract = "We developed an unsupervised machine learning algorithm and applied it to big corneal parameters to identify and monitor keratoconus stages. A big dataset of corneal swept source optical coherence tomography (OCT) images of 12,242 eyes acquired from SS-1000 CASIA OCT Imaging Systems in multiple centers across Japan was assembled. A total of 3,156 eyes with valid Ectasia Status Index (ESI) between zero and 100{\%} were selected for the downstream analysis. Four hundred and twenty corneal topography, elevation, and pachymetry parameters (excluding ESI Keratoconus indices) were selected. The algorithm included three major steps. 1) Principal component analysis (PCA) was used to linearly reduce the dimensionality of the input data from 420 to eight significant principal components. 2) Manifold learning was used to further reducing the selected principal components nonlinearly to two eigen-parameters. 3) Finally, a density-based clustering was applied to the eigen-parameters to identify eyes with keratoconus. Visualization of clusters in 2-D space was used to validate the quality of learning subjectively and ESI was used to assess the accuracy of the identified clusters objectively. The proposed method identified four clusters; I: a cluster composed of mostly normal eyes (224 eyes with ESI equal to zero, 23 eyes with ESI between five and 29, and nine eyes with ESI greater than 29), II: a cluster composed of mostly healthy eyes and eyes with forme fruste keratoconus (1772 eyes with ESI equal to zero, 698 eyes with ESI between five and 29, and 117 eyes with ESI greater than 29), III: a cluster composed of mostly eyes with mild keratoconus stage (184 eyes with ESI greater than 29, 74 eyes with ESI between five and 29, and 6 eyes with ESI equal to zero), and IV: a cluster composed of eyes with mostly advanced keratoconus stage (80 eyes had ESI greater than 29 and 1 eye had ESI between five and 29). We found that keratoconus status and severity can be well identified using unsupervised machine learning algorithms along with linear and non-linear corneal data transformation. The proposed method can better identify and visualize the keratoconus stages.",
author = "Siamak Yousefi and Ebrahim Yousefi and Hidenori Takahashi and Takahiko Hayashi and Hironobu Tampo and Satoru Inoda and Yusuke Arai and Penny Asbell",
year = "2018",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0205998",
language = "English (US)",
volume = "13",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "11",

}

TY - JOUR

T1 - Keratoconus severity identification using unsupervised machine learning

AU - Yousefi, Siamak

AU - Yousefi, Ebrahim

AU - Takahashi, Hidenori

AU - Hayashi, Takahiko

AU - Tampo, Hironobu

AU - Inoda, Satoru

AU - Arai, Yusuke

AU - Asbell, Penny

PY - 2018/1/1

Y1 - 2018/1/1

N2 - We developed an unsupervised machine learning algorithm and applied it to big corneal parameters to identify and monitor keratoconus stages. A big dataset of corneal swept source optical coherence tomography (OCT) images of 12,242 eyes acquired from SS-1000 CASIA OCT Imaging Systems in multiple centers across Japan was assembled. A total of 3,156 eyes with valid Ectasia Status Index (ESI) between zero and 100% were selected for the downstream analysis. Four hundred and twenty corneal topography, elevation, and pachymetry parameters (excluding ESI Keratoconus indices) were selected. The algorithm included three major steps. 1) Principal component analysis (PCA) was used to linearly reduce the dimensionality of the input data from 420 to eight significant principal components. 2) Manifold learning was used to further reducing the selected principal components nonlinearly to two eigen-parameters. 3) Finally, a density-based clustering was applied to the eigen-parameters to identify eyes with keratoconus. Visualization of clusters in 2-D space was used to validate the quality of learning subjectively and ESI was used to assess the accuracy of the identified clusters objectively. The proposed method identified four clusters; I: a cluster composed of mostly normal eyes (224 eyes with ESI equal to zero, 23 eyes with ESI between five and 29, and nine eyes with ESI greater than 29), II: a cluster composed of mostly healthy eyes and eyes with forme fruste keratoconus (1772 eyes with ESI equal to zero, 698 eyes with ESI between five and 29, and 117 eyes with ESI greater than 29), III: a cluster composed of mostly eyes with mild keratoconus stage (184 eyes with ESI greater than 29, 74 eyes with ESI between five and 29, and 6 eyes with ESI equal to zero), and IV: a cluster composed of eyes with mostly advanced keratoconus stage (80 eyes had ESI greater than 29 and 1 eye had ESI between five and 29). We found that keratoconus status and severity can be well identified using unsupervised machine learning algorithms along with linear and non-linear corneal data transformation. The proposed method can better identify and visualize the keratoconus stages.

AB - We developed an unsupervised machine learning algorithm and applied it to big corneal parameters to identify and monitor keratoconus stages. A big dataset of corneal swept source optical coherence tomography (OCT) images of 12,242 eyes acquired from SS-1000 CASIA OCT Imaging Systems in multiple centers across Japan was assembled. A total of 3,156 eyes with valid Ectasia Status Index (ESI) between zero and 100% were selected for the downstream analysis. Four hundred and twenty corneal topography, elevation, and pachymetry parameters (excluding ESI Keratoconus indices) were selected. The algorithm included three major steps. 1) Principal component analysis (PCA) was used to linearly reduce the dimensionality of the input data from 420 to eight significant principal components. 2) Manifold learning was used to further reducing the selected principal components nonlinearly to two eigen-parameters. 3) Finally, a density-based clustering was applied to the eigen-parameters to identify eyes with keratoconus. Visualization of clusters in 2-D space was used to validate the quality of learning subjectively and ESI was used to assess the accuracy of the identified clusters objectively. The proposed method identified four clusters; I: a cluster composed of mostly normal eyes (224 eyes with ESI equal to zero, 23 eyes with ESI between five and 29, and nine eyes with ESI greater than 29), II: a cluster composed of mostly healthy eyes and eyes with forme fruste keratoconus (1772 eyes with ESI equal to zero, 698 eyes with ESI between five and 29, and 117 eyes with ESI greater than 29), III: a cluster composed of mostly eyes with mild keratoconus stage (184 eyes with ESI greater than 29, 74 eyes with ESI between five and 29, and 6 eyes with ESI equal to zero), and IV: a cluster composed of eyes with mostly advanced keratoconus stage (80 eyes had ESI greater than 29 and 1 eye had ESI between five and 29). We found that keratoconus status and severity can be well identified using unsupervised machine learning algorithms along with linear and non-linear corneal data transformation. The proposed method can better identify and visualize the keratoconus stages.

UR - http://www.scopus.com/inward/record.url?scp=85056247855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056247855&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0205998

DO - 10.1371/journal.pone.0205998

M3 - Article

VL - 13

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 11

M1 - e0205998

ER -