Feature-based glaucomatous progression prediction using scanning laser polarimetry (SLP) data

P. Y. Kim, K. M. Iftekharuddin, P. Gunvant, M. Tóth, A. Garas, G. Holló, E. A. Essock

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

2 Citations (Scopus)

Abstract

In this work, we investigate the effectiveness of a novel fractal feature-based technique in predicting glaucomatous progression using the retinal nerve fiber layer (RNFL) thickness measurement data. The technique is used to analyze GDx variable corneal compensator (GDx-VCC) scanning laser polarimeter (SLP) data from one eye of 96 study participants (14 progressors, 45 non-progressors, and 37 ocular normal patients). The novel feature is obtained by using a 2D box-counting (BC) method, which utilizes pseudo 2D images from 1D temporal, superior, nasal, inferior, temporal (TSNIT) RNFL data. For statistical performance evaluation and comparison, we compute sensitivity, specificity and area under receiver operating curve (AUROC) for fractal analysis (FA) and other existing feature-based techniques such as fast Fourier analysis (FFA) and wavelet-Fourier analysis (WFA). The AUROCs indicating discrimination between progressors and non-progressors using the classifiers with the selected FA, WFA, and FFA features are 0.82, 0.78 and 0.82 respectively for 6 months prior to progression and 0.63, 0.69 and 0.73 respectively 18 months prior to progression. We then use the same classifiers to compute specificity in ocular normal patients. The corresponding specificities for ocular normal patients are 0.86, 0.76 and 0.86 for FFA, WFA and FA methods, respectively.

Original languageEnglish
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7963
DOIs
Publication statusPublished - 2011
EventMedical Imaging 2011: Computer-Aided Diagnosis - Lake Buena Vista, FL, United States
Duration: Feb 15 2011Feb 17 2011

Other

OtherMedical Imaging 2011: Computer-Aided Diagnosis
CountryUnited States
CityLake Buena Vista, FL
Period2/15/112/17/11

Fingerprint

Scanning Laser Polarimetry
Polarimeters
Fourier analysis
polarimetry
Fourier Analysis
progressions
Fractals
Scanning
Wavelet Analysis
scanning
Lasers
fractals
predictions
lasers
nerve fibers
classifiers
Nerve Fibers
Classifiers
Thickness measurement
Fibers

Keywords

  • Fourier analysis
  • Fractal analysis
  • Glaucomatous progression
  • scanning laser polarimetry
  • Wavelet analysis

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Kim, P. Y., Iftekharuddin, K. M., Gunvant, P., Tóth, M., Garas, A., Holló, G., & Essock, E. A. (2011). Feature-based glaucomatous progression prediction using scanning laser polarimetry (SLP) data. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 7963). [79633T] https://doi.org/10.1117/12.877744

Feature-based glaucomatous progression prediction using scanning laser polarimetry (SLP) data. / Kim, P. Y.; Iftekharuddin, K. M.; Gunvant, P.; Tóth, M.; Garas, A.; Holló, G.; Essock, E. A.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963 2011. 79633T.

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

Kim, PY, Iftekharuddin, KM, Gunvant, P, Tóth, M, Garas, A, Holló, G & Essock, EA 2011, Feature-based glaucomatous progression prediction using scanning laser polarimetry (SLP) data. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 7963, 79633T, Medical Imaging 2011: Computer-Aided Diagnosis, Lake Buena Vista, FL, United States, 2/15/11. https://doi.org/10.1117/12.877744
Kim PY, Iftekharuddin KM, Gunvant P, Tóth M, Garas A, Holló G et al. Feature-based glaucomatous progression prediction using scanning laser polarimetry (SLP) data. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963. 2011. 79633T https://doi.org/10.1117/12.877744
Kim, P. Y. ; Iftekharuddin, K. M. ; Gunvant, P. ; Tóth, M. ; Garas, A. ; Holló, G. ; Essock, E. A. / Feature-based glaucomatous progression prediction using scanning laser polarimetry (SLP) data. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963 2011.
@inproceedings{902c93d8aa0f425dbf8b4acfeb722560,
title = "Feature-based glaucomatous progression prediction using scanning laser polarimetry (SLP) data",
abstract = "In this work, we investigate the effectiveness of a novel fractal feature-based technique in predicting glaucomatous progression using the retinal nerve fiber layer (RNFL) thickness measurement data. The technique is used to analyze GDx variable corneal compensator (GDx-VCC) scanning laser polarimeter (SLP) data from one eye of 96 study participants (14 progressors, 45 non-progressors, and 37 ocular normal patients). The novel feature is obtained by using a 2D box-counting (BC) method, which utilizes pseudo 2D images from 1D temporal, superior, nasal, inferior, temporal (TSNIT) RNFL data. For statistical performance evaluation and comparison, we compute sensitivity, specificity and area under receiver operating curve (AUROC) for fractal analysis (FA) and other existing feature-based techniques such as fast Fourier analysis (FFA) and wavelet-Fourier analysis (WFA). The AUROCs indicating discrimination between progressors and non-progressors using the classifiers with the selected FA, WFA, and FFA features are 0.82, 0.78 and 0.82 respectively for 6 months prior to progression and 0.63, 0.69 and 0.73 respectively 18 months prior to progression. We then use the same classifiers to compute specificity in ocular normal patients. The corresponding specificities for ocular normal patients are 0.86, 0.76 and 0.86 for FFA, WFA and FA methods, respectively.",
keywords = "Fourier analysis, Fractal analysis, Glaucomatous progression, scanning laser polarimetry, Wavelet analysis",
author = "Kim, {P. Y.} and Iftekharuddin, {K. M.} and P. Gunvant and M. T{\'o}th and A. Garas and G. Holl{\'o} and Essock, {E. A.}",
year = "2011",
doi = "10.1117/12.877744",
language = "English",
isbn = "9780819485052",
volume = "7963",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Feature-based glaucomatous progression prediction using scanning laser polarimetry (SLP) data

AU - Kim, P. Y.

AU - Iftekharuddin, K. M.

AU - Gunvant, P.

AU - Tóth, M.

AU - Garas, A.

AU - Holló, G.

AU - Essock, E. A.

PY - 2011

Y1 - 2011

N2 - In this work, we investigate the effectiveness of a novel fractal feature-based technique in predicting glaucomatous progression using the retinal nerve fiber layer (RNFL) thickness measurement data. The technique is used to analyze GDx variable corneal compensator (GDx-VCC) scanning laser polarimeter (SLP) data from one eye of 96 study participants (14 progressors, 45 non-progressors, and 37 ocular normal patients). The novel feature is obtained by using a 2D box-counting (BC) method, which utilizes pseudo 2D images from 1D temporal, superior, nasal, inferior, temporal (TSNIT) RNFL data. For statistical performance evaluation and comparison, we compute sensitivity, specificity and area under receiver operating curve (AUROC) for fractal analysis (FA) and other existing feature-based techniques such as fast Fourier analysis (FFA) and wavelet-Fourier analysis (WFA). The AUROCs indicating discrimination between progressors and non-progressors using the classifiers with the selected FA, WFA, and FFA features are 0.82, 0.78 and 0.82 respectively for 6 months prior to progression and 0.63, 0.69 and 0.73 respectively 18 months prior to progression. We then use the same classifiers to compute specificity in ocular normal patients. The corresponding specificities for ocular normal patients are 0.86, 0.76 and 0.86 for FFA, WFA and FA methods, respectively.

AB - In this work, we investigate the effectiveness of a novel fractal feature-based technique in predicting glaucomatous progression using the retinal nerve fiber layer (RNFL) thickness measurement data. The technique is used to analyze GDx variable corneal compensator (GDx-VCC) scanning laser polarimeter (SLP) data from one eye of 96 study participants (14 progressors, 45 non-progressors, and 37 ocular normal patients). The novel feature is obtained by using a 2D box-counting (BC) method, which utilizes pseudo 2D images from 1D temporal, superior, nasal, inferior, temporal (TSNIT) RNFL data. For statistical performance evaluation and comparison, we compute sensitivity, specificity and area under receiver operating curve (AUROC) for fractal analysis (FA) and other existing feature-based techniques such as fast Fourier analysis (FFA) and wavelet-Fourier analysis (WFA). The AUROCs indicating discrimination between progressors and non-progressors using the classifiers with the selected FA, WFA, and FFA features are 0.82, 0.78 and 0.82 respectively for 6 months prior to progression and 0.63, 0.69 and 0.73 respectively 18 months prior to progression. We then use the same classifiers to compute specificity in ocular normal patients. The corresponding specificities for ocular normal patients are 0.86, 0.76 and 0.86 for FFA, WFA and FA methods, respectively.

KW - Fourier analysis

KW - Fractal analysis

KW - Glaucomatous progression

KW - scanning laser polarimetry

KW - Wavelet analysis

UR - http://www.scopus.com/inward/record.url?scp=79955759896&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955759896&partnerID=8YFLogxK

U2 - 10.1117/12.877744

DO - 10.1117/12.877744

M3 - Conference contribution

SN - 9780819485052

VL - 7963

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -