Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Machine learning classifiers for glaucoma diagnosis based on classification of retinal nerve fibre layer thickness parameters measured by Stratus OCT.

Bizios, Dimitrios LU orcid ; Heijl, Anders LU ; Hougaard, Jesper LU and Bengtsson, Boel LU (2010) In Acta Ophthalmologica 88. p.44-52
Abstract
Abstract. Purpose: To compare the performance of two machine learning classifiers (MLCs), artificial neural networks (ANNs) and support vector machines (SVMs), with input based on retinal nerve fibre layer thickness (RNFLT) measurements by optical coherence tomography (OCT), on the diagnosis of glaucoma, and to assess the effects of different input parameters. Methods: We analysed Stratus OCT data from 90 healthy persons and 62 glaucoma patients. Performance of MLCs was compared using conventional OCT RNFLT parameters plus novel parameters such as minimum RNFLT values, 10th and 90th percentiles of measured RNFLT, and transformations of A-scan measurements. For each input parameter and MLC, the area under the receiver operating... (More)
Abstract. Purpose: To compare the performance of two machine learning classifiers (MLCs), artificial neural networks (ANNs) and support vector machines (SVMs), with input based on retinal nerve fibre layer thickness (RNFLT) measurements by optical coherence tomography (OCT), on the diagnosis of glaucoma, and to assess the effects of different input parameters. Methods: We analysed Stratus OCT data from 90 healthy persons and 62 glaucoma patients. Performance of MLCs was compared using conventional OCT RNFLT parameters plus novel parameters such as minimum RNFLT values, 10th and 90th percentiles of measured RNFLT, and transformations of A-scan measurements. For each input parameter and MLC, the area under the receiver operating characteristic curve (AROC) was calculated. Results: There were no statistically significant differences between ANNs and SVMs. The best AROCs for both ANN (0.982, 95%CI: 0.966-0.999) and SVM (0.989, 95% CI: 0.979-1.0) were based on input of transformed A-scan measurements. Our SVM trained on this input performed better than ANNs or SVMs trained on any of the single RNFLT parameters (p </= 0.038). The performance of ANNs and SVMs trained on minimum thickness values and the 10th and 90th percentiles were at least as good as ANNs and SVMs with input based on the conventional RNFLT parameters. Conclusion: No differences between ANN and SVM were observed in this study. Both MLCs performed very well, with similar diagnostic performance. Input parameters have a larger impact on diagnostic performance than the type of machine classifier. Our results suggest that parameters based on transformed A-scan thickness measurements of the RNFL processed by machine classifiers can improve OCT-based glaucoma diagnosis. (Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Acta Ophthalmologica
volume
88
pages
44 - 52
publisher
Wiley-Blackwell
external identifiers
  • wos:000274168900009
  • pmid:20064122
  • scopus:76149109733
  • pmid:20064122
ISSN
1755-3768
DOI
10.1111/j.1755-3768.2009.01784.x
language
English
LU publication?
yes
id
238dd5e9-7182-4f08-bb79-c760d1b70d5f (old id 1541214)
alternative location
http://www.ncbi.nlm.nih.gov/pubmed/20064122?dopt=Abstract
date added to LUP
2016-04-04 08:10:22
date last changed
2022-07-31 23:51:02
@article{238dd5e9-7182-4f08-bb79-c760d1b70d5f,
  abstract     = {{Abstract. Purpose: To compare the performance of two machine learning classifiers (MLCs), artificial neural networks (ANNs) and support vector machines (SVMs), with input based on retinal nerve fibre layer thickness (RNFLT) measurements by optical coherence tomography (OCT), on the diagnosis of glaucoma, and to assess the effects of different input parameters. Methods: We analysed Stratus OCT data from 90 healthy persons and 62 glaucoma patients. Performance of MLCs was compared using conventional OCT RNFLT parameters plus novel parameters such as minimum RNFLT values, 10th and 90th percentiles of measured RNFLT, and transformations of A-scan measurements. For each input parameter and MLC, the area under the receiver operating characteristic curve (AROC) was calculated. Results: There were no statistically significant differences between ANNs and SVMs. The best AROCs for both ANN (0.982, 95%CI: 0.966-0.999) and SVM (0.989, 95% CI: 0.979-1.0) were based on input of transformed A-scan measurements. Our SVM trained on this input performed better than ANNs or SVMs trained on any of the single RNFLT parameters (p &lt;/= 0.038). The performance of ANNs and SVMs trained on minimum thickness values and the 10th and 90th percentiles were at least as good as ANNs and SVMs with input based on the conventional RNFLT parameters. Conclusion: No differences between ANN and SVM were observed in this study. Both MLCs performed very well, with similar diagnostic performance. Input parameters have a larger impact on diagnostic performance than the type of machine classifier. Our results suggest that parameters based on transformed A-scan thickness measurements of the RNFL processed by machine classifiers can improve OCT-based glaucoma diagnosis.}},
  author       = {{Bizios, Dimitrios and Heijl, Anders and Hougaard, Jesper and Bengtsson, Boel}},
  issn         = {{1755-3768}},
  language     = {{eng}},
  pages        = {{44--52}},
  publisher    = {{Wiley-Blackwell}},
  series       = {{Acta Ophthalmologica}},
  title        = {{Machine learning classifiers for glaucoma diagnosis based on classification of retinal nerve fibre layer thickness parameters measured by Stratus OCT.}},
  url          = {{http://dx.doi.org/10.1111/j.1755-3768.2009.01784.x}},
  doi          = {{10.1111/j.1755-3768.2009.01784.x}},
  volume       = {{88}},
  year         = {{2010}},
}