Integration of scheimpflug-based corneal tomography and biomechanical assessments for enhancing ectasia detection

Renato Ambrósio, Bernardo T. Lopes, Fernando Faria-Correia, Marcella Q. Salomão, Jens Bühren, Cynthia J. Roberts, Ahmed Elsheikh, Riccardo Vinciguerra, Paolo Vinciguerra

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

Purpose: To present the Tomographic and Biomechanical Index (TBI), which combines Scheimpflug-based corneal tomography and biomechanics for enhancing ectasia detection. Methods: Patients from different continents were retrospectively studied. The normal group included 1 eye randomly selected from 480 patients with normal corneas and the keratoconus group included 1 eye randomly selected from 204 patients with keratoconus. There were two groups: 72 ectatic eyes with no surgery from 94 patients with very asymmetric ectasia (VAE-E group) and the fellow eyes of these patients with normal topography (VAE-NT group). Pentacam HR and Corvis ST (Oculus Optikgeräte GmbH, Wetzlar, Germany) parameters were analyzed and combined using different artificial intelligence methods. The accuracies for detecting ectasia of the Belin/Ambrósio Deviation (BAD-D) and Corvis Biomechanical Index (CBI) were compared to the TBI, considering the areas under receiver operating characteristic curves (AUROCs). Results: The random forest method with leave-one-out cross-validation (RF/LOOCV) provided the best artificial intelligence model. The AUROC for detecting ectasia (keratoconus, VAE-E, and VAE-NT groups) of the TBI was 0.996, which was statistically higher (DeLong et al., P < .001) than the BAD-D (0.956) and CBI (0.936). The TBI cut-off value of 0.79 provided 100% sensitivity for detecting clinical ectasia (keratoconus and VAE-E groups) with 100% specificity. The AUROCs for the TBI, BAD-D, and CBI were 0.985, 0.839, and 0.822 in the VAE-NT group (DeLong et al., P < .001). An optimized TBI cut-off value of 0.29 provided 90.4% sensitivity with 96% specificity in the VAE-NT group. Conclusions: The TBI generated by the RF/LOOCV provided greater accuracy for detecting ectasia than other techniques. The TBI was sensitive for detecting subclinical (fruste) ectasia among eyes with normal topography in very asymmetric patients. The TBI may also confirm unilateral ectasia, potentially characterizing the inherent ectasia susceptibility of the cornea, which should be the subject of future studies.

Original languageEnglish
Pages (from-to)434-443
Number of pages10
JournalJournal of Refractive Surgery
Volume33
Issue number7
DOIs
Publication statusPublished - Jul 1 2017

Fingerprint

Pathologic Dilatations
Tomography
Keratoconus
ROC Curve
Artificial Intelligence
Cornea
Biomechanical Phenomena
Germany

ASJC Scopus subject areas

  • Surgery
  • Ophthalmology

Cite this

Integration of scheimpflug-based corneal tomography and biomechanical assessments for enhancing ectasia detection. / Ambrósio, Renato; Lopes, Bernardo T.; Faria-Correia, Fernando; Salomão, Marcella Q.; Bühren, Jens; Roberts, Cynthia J.; Elsheikh, Ahmed; Vinciguerra, Riccardo; Vinciguerra, Paolo.

In: Journal of Refractive Surgery, Vol. 33, No. 7, 01.07.2017, p. 434-443.

Research output: Contribution to journalArticle

Ambrósio, R, Lopes, BT, Faria-Correia, F, Salomão, MQ, Bühren, J, Roberts, CJ, Elsheikh, A, Vinciguerra, R & Vinciguerra, P 2017, 'Integration of scheimpflug-based corneal tomography and biomechanical assessments for enhancing ectasia detection', Journal of Refractive Surgery, vol. 33, no. 7, pp. 434-443. https://doi.org/10.3928/1081597X-20170426-02
Ambrósio, Renato ; Lopes, Bernardo T. ; Faria-Correia, Fernando ; Salomão, Marcella Q. ; Bühren, Jens ; Roberts, Cynthia J. ; Elsheikh, Ahmed ; Vinciguerra, Riccardo ; Vinciguerra, Paolo. / Integration of scheimpflug-based corneal tomography and biomechanical assessments for enhancing ectasia detection. In: Journal of Refractive Surgery. 2017 ; Vol. 33, No. 7. pp. 434-443.
@article{99299d64f02748fe85b25a8fac2569a8,
title = "Integration of scheimpflug-based corneal tomography and biomechanical assessments for enhancing ectasia detection",
abstract = "Purpose: To present the Tomographic and Biomechanical Index (TBI), which combines Scheimpflug-based corneal tomography and biomechanics for enhancing ectasia detection. Methods: Patients from different continents were retrospectively studied. The normal group included 1 eye randomly selected from 480 patients with normal corneas and the keratoconus group included 1 eye randomly selected from 204 patients with keratoconus. There were two groups: 72 ectatic eyes with no surgery from 94 patients with very asymmetric ectasia (VAE-E group) and the fellow eyes of these patients with normal topography (VAE-NT group). Pentacam HR and Corvis ST (Oculus Optikger{\"a}te GmbH, Wetzlar, Germany) parameters were analyzed and combined using different artificial intelligence methods. The accuracies for detecting ectasia of the Belin/Ambr{\'o}sio Deviation (BAD-D) and Corvis Biomechanical Index (CBI) were compared to the TBI, considering the areas under receiver operating characteristic curves (AUROCs). Results: The random forest method with leave-one-out cross-validation (RF/LOOCV) provided the best artificial intelligence model. The AUROC for detecting ectasia (keratoconus, VAE-E, and VAE-NT groups) of the TBI was 0.996, which was statistically higher (DeLong et al., P < .001) than the BAD-D (0.956) and CBI (0.936). The TBI cut-off value of 0.79 provided 100{\%} sensitivity for detecting clinical ectasia (keratoconus and VAE-E groups) with 100{\%} specificity. The AUROCs for the TBI, BAD-D, and CBI were 0.985, 0.839, and 0.822 in the VAE-NT group (DeLong et al., P < .001). An optimized TBI cut-off value of 0.29 provided 90.4{\%} sensitivity with 96{\%} specificity in the VAE-NT group. Conclusions: The TBI generated by the RF/LOOCV provided greater accuracy for detecting ectasia than other techniques. The TBI was sensitive for detecting subclinical (fruste) ectasia among eyes with normal topography in very asymmetric patients. The TBI may also confirm unilateral ectasia, potentially characterizing the inherent ectasia susceptibility of the cornea, which should be the subject of future studies.",
author = "Renato Ambr{\'o}sio and Lopes, {Bernardo T.} and Fernando Faria-Correia and Salom{\~a}o, {Marcella Q.} and Jens B{\"u}hren and Roberts, {Cynthia J.} and Ahmed Elsheikh and Riccardo Vinciguerra and Paolo Vinciguerra",
year = "2017",
month = "7",
day = "1",
doi = "10.3928/1081597X-20170426-02",
language = "English",
volume = "33",
pages = "434--443",
journal = "Journal of Refractive Surgery",
issn = "1081-597X",
publisher = "Slack Incorporated",
number = "7",

}

TY - JOUR

T1 - Integration of scheimpflug-based corneal tomography and biomechanical assessments for enhancing ectasia detection

AU - Ambrósio, Renato

AU - Lopes, Bernardo T.

AU - Faria-Correia, Fernando

AU - Salomão, Marcella Q.

AU - Bühren, Jens

AU - Roberts, Cynthia J.

AU - Elsheikh, Ahmed

AU - Vinciguerra, Riccardo

AU - Vinciguerra, Paolo

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Purpose: To present the Tomographic and Biomechanical Index (TBI), which combines Scheimpflug-based corneal tomography and biomechanics for enhancing ectasia detection. Methods: Patients from different continents were retrospectively studied. The normal group included 1 eye randomly selected from 480 patients with normal corneas and the keratoconus group included 1 eye randomly selected from 204 patients with keratoconus. There were two groups: 72 ectatic eyes with no surgery from 94 patients with very asymmetric ectasia (VAE-E group) and the fellow eyes of these patients with normal topography (VAE-NT group). Pentacam HR and Corvis ST (Oculus Optikgeräte GmbH, Wetzlar, Germany) parameters were analyzed and combined using different artificial intelligence methods. The accuracies for detecting ectasia of the Belin/Ambrósio Deviation (BAD-D) and Corvis Biomechanical Index (CBI) were compared to the TBI, considering the areas under receiver operating characteristic curves (AUROCs). Results: The random forest method with leave-one-out cross-validation (RF/LOOCV) provided the best artificial intelligence model. The AUROC for detecting ectasia (keratoconus, VAE-E, and VAE-NT groups) of the TBI was 0.996, which was statistically higher (DeLong et al., P < .001) than the BAD-D (0.956) and CBI (0.936). The TBI cut-off value of 0.79 provided 100% sensitivity for detecting clinical ectasia (keratoconus and VAE-E groups) with 100% specificity. The AUROCs for the TBI, BAD-D, and CBI were 0.985, 0.839, and 0.822 in the VAE-NT group (DeLong et al., P < .001). An optimized TBI cut-off value of 0.29 provided 90.4% sensitivity with 96% specificity in the VAE-NT group. Conclusions: The TBI generated by the RF/LOOCV provided greater accuracy for detecting ectasia than other techniques. The TBI was sensitive for detecting subclinical (fruste) ectasia among eyes with normal topography in very asymmetric patients. The TBI may also confirm unilateral ectasia, potentially characterizing the inherent ectasia susceptibility of the cornea, which should be the subject of future studies.

AB - Purpose: To present the Tomographic and Biomechanical Index (TBI), which combines Scheimpflug-based corneal tomography and biomechanics for enhancing ectasia detection. Methods: Patients from different continents were retrospectively studied. The normal group included 1 eye randomly selected from 480 patients with normal corneas and the keratoconus group included 1 eye randomly selected from 204 patients with keratoconus. There were two groups: 72 ectatic eyes with no surgery from 94 patients with very asymmetric ectasia (VAE-E group) and the fellow eyes of these patients with normal topography (VAE-NT group). Pentacam HR and Corvis ST (Oculus Optikgeräte GmbH, Wetzlar, Germany) parameters were analyzed and combined using different artificial intelligence methods. The accuracies for detecting ectasia of the Belin/Ambrósio Deviation (BAD-D) and Corvis Biomechanical Index (CBI) were compared to the TBI, considering the areas under receiver operating characteristic curves (AUROCs). Results: The random forest method with leave-one-out cross-validation (RF/LOOCV) provided the best artificial intelligence model. The AUROC for detecting ectasia (keratoconus, VAE-E, and VAE-NT groups) of the TBI was 0.996, which was statistically higher (DeLong et al., P < .001) than the BAD-D (0.956) and CBI (0.936). The TBI cut-off value of 0.79 provided 100% sensitivity for detecting clinical ectasia (keratoconus and VAE-E groups) with 100% specificity. The AUROCs for the TBI, BAD-D, and CBI were 0.985, 0.839, and 0.822 in the VAE-NT group (DeLong et al., P < .001). An optimized TBI cut-off value of 0.29 provided 90.4% sensitivity with 96% specificity in the VAE-NT group. Conclusions: The TBI generated by the RF/LOOCV provided greater accuracy for detecting ectasia than other techniques. The TBI was sensitive for detecting subclinical (fruste) ectasia among eyes with normal topography in very asymmetric patients. The TBI may also confirm unilateral ectasia, potentially characterizing the inherent ectasia susceptibility of the cornea, which should be the subject of future studies.

UR - http://www.scopus.com/inward/record.url?scp=85022322998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022322998&partnerID=8YFLogxK

U2 - 10.3928/1081597X-20170426-02

DO - 10.3928/1081597X-20170426-02

M3 - Article

AN - SCOPUS:85022322998

VL - 33

SP - 434

EP - 443

JO - Journal of Refractive Surgery

JF - Journal of Refractive Surgery

SN - 1081-597X

IS - 7

ER -