Two-dimensional plane for multi-scale quantification of corneal subbasal nerve tortuosity

Roberto Annunziata, Ahmad Kheirkhah, Shruti Aggarwal, Bernardo M. Cavalcanti, Pedram Hamrah, Emanuele Trucco (Lead / Corresponding author)

Research output: Contribution to journalArticle

5 Citations (Scopus)
66 Downloads (Pure)

Abstract

PURPOSE. To assess the performance of a novel system for automated tortuosity estimation and interpretation. 

METHODS. A supervised strategy (driven by observers’ grading) was employed to automatically identify the combination of tortuosity measures (i.e., tortuosity representation) leading to the best agreement with the observers. We investigated 18 tortuosity measures including curvature and density of inflection points, computed at multiple spatial scales. To leverage tortuosity interpretation, we propose the tortuosity plane (TP) onto which each image is mapped. Experiments were carried out on 140 images of subbasal nerve plexus of the central cornea, covering four levels of tortuosity. Three experienced observers graded each image independently. 

RESULTS. The best tortuosity representation was the combination of mean curvature at spatial scales 2 and 5. These tortuosity measures were the axes of the proposed TP (interpretation). The system for tortuosity estimation revealed strong agreement with the observers on a global and per-level basis. The agreement with each observer (Spearman’s correlation) was statistically significant (αs = 0.05, P <0.0001) and higher than that of at least one of the other observers in two out of three cases (ρOUR = 0.7594 versus ρObs3 = 0.7225; ρOUR = 0.8880 versus ρObs1 = 0.8017, ρObs3 = 0.7315). Based on paired-sample t-tests, these improvements were significant (P <0.001). 

CONCLUSIONS. Our automated system stratifies images by four tortuosity levels (discrete scale) matching or exceeding the accuracy of experienced observers. Of importance, the TP allows the assessment of tortuosity on a two-dimensional continuous scale, thus leading to a finer discrimination among images.

Original languageEnglish
Pages (from-to)1132-1139
Number of pages8
JournalInvestigative Ophthalmology & Visual Science
Volume57
Issue number3
DOIs
Publication statusPublished - 1 Mar 2016

Fingerprint

Cornea

Keywords

  • Confocal microscopy
  • Corneal subbasal nerve plexus
  • Tortuosity plane

Cite this

Annunziata, Roberto ; Kheirkhah, Ahmad ; Aggarwal, Shruti ; Cavalcanti, Bernardo M. ; Hamrah, Pedram ; Trucco, Emanuele. / Two-dimensional plane for multi-scale quantification of corneal subbasal nerve tortuosity. In: Investigative Ophthalmology & Visual Science. 2016 ; Vol. 57, No. 3. pp. 1132-1139.
@article{0dee9d74cd824142b81b3de1061446d6,
title = "Two-dimensional plane for multi-scale quantification of corneal subbasal nerve tortuosity",
abstract = "PURPOSE. To assess the performance of a novel system for automated tortuosity estimation and interpretation. METHODS. A supervised strategy (driven by observers’ grading) was employed to automatically identify the combination of tortuosity measures (i.e., tortuosity representation) leading to the best agreement with the observers. We investigated 18 tortuosity measures including curvature and density of inflection points, computed at multiple spatial scales. To leverage tortuosity interpretation, we propose the tortuosity plane (TP) onto which each image is mapped. Experiments were carried out on 140 images of subbasal nerve plexus of the central cornea, covering four levels of tortuosity. Three experienced observers graded each image independently. RESULTS. The best tortuosity representation was the combination of mean curvature at spatial scales 2 and 5. These tortuosity measures were the axes of the proposed TP (interpretation). The system for tortuosity estimation revealed strong agreement with the observers on a global and per-level basis. The agreement with each observer (Spearman’s correlation) was statistically significant (αs = 0.05, P <0.0001) and higher than that of at least one of the other observers in two out of three cases (ρOUR = 0.7594 versus ρObs3 = 0.7225; ρOUR = 0.8880 versus ρObs1 = 0.8017, ρObs3 = 0.7315). Based on paired-sample t-tests, these improvements were significant (P <0.001). CONCLUSIONS. Our automated system stratifies images by four tortuosity levels (discrete scale) matching or exceeding the accuracy of experienced observers. Of importance, the TP allows the assessment of tortuosity on a two-dimensional continuous scale, thus leading to a finer discrimination among images.",
keywords = "Confocal microscopy, Corneal subbasal nerve plexus, Tortuosity plane",
author = "Roberto Annunziata and Ahmad Kheirkhah and Shruti Aggarwal and Cavalcanti, {Bernardo M.} and Pedram Hamrah and Emanuele Trucco",
note = "Supported by European Union Marie Sklodowska-Curie Initial Training Network Retinal Vascular Modelling, Measurement And Diagnosis (REVAMMAD), Project Number 316990 (RA, ET) and by the National Institutes of Health Grant NIH R01-EY022695 (PH), Falk Medical Research Foundation (PH), and Massachusetts Eye and Ear Infirmary Foundation (PH).",
year = "2016",
month = "3",
day = "1",
doi = "10.1167/iovs.15-18513",
language = "English",
volume = "57",
pages = "1132--1139",
journal = "Investigative Ophthalmology & Visual Science",
issn = "0146-0404",
publisher = "Association for Research in Vision and Ophthalmology",
number = "3",

}

Two-dimensional plane for multi-scale quantification of corneal subbasal nerve tortuosity. / Annunziata, Roberto; Kheirkhah, Ahmad; Aggarwal, Shruti; Cavalcanti, Bernardo M.; Hamrah, Pedram; Trucco, Emanuele (Lead / Corresponding author).

In: Investigative Ophthalmology & Visual Science, Vol. 57, No. 3, 01.03.2016, p. 1132-1139.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Two-dimensional plane for multi-scale quantification of corneal subbasal nerve tortuosity

AU - Annunziata, Roberto

AU - Kheirkhah, Ahmad

AU - Aggarwal, Shruti

AU - Cavalcanti, Bernardo M.

AU - Hamrah, Pedram

AU - Trucco, Emanuele

N1 - Supported by European Union Marie Sklodowska-Curie Initial Training Network Retinal Vascular Modelling, Measurement And Diagnosis (REVAMMAD), Project Number 316990 (RA, ET) and by the National Institutes of Health Grant NIH R01-EY022695 (PH), Falk Medical Research Foundation (PH), and Massachusetts Eye and Ear Infirmary Foundation (PH).

PY - 2016/3/1

Y1 - 2016/3/1

N2 - PURPOSE. To assess the performance of a novel system for automated tortuosity estimation and interpretation. METHODS. A supervised strategy (driven by observers’ grading) was employed to automatically identify the combination of tortuosity measures (i.e., tortuosity representation) leading to the best agreement with the observers. We investigated 18 tortuosity measures including curvature and density of inflection points, computed at multiple spatial scales. To leverage tortuosity interpretation, we propose the tortuosity plane (TP) onto which each image is mapped. Experiments were carried out on 140 images of subbasal nerve plexus of the central cornea, covering four levels of tortuosity. Three experienced observers graded each image independently. RESULTS. The best tortuosity representation was the combination of mean curvature at spatial scales 2 and 5. These tortuosity measures were the axes of the proposed TP (interpretation). The system for tortuosity estimation revealed strong agreement with the observers on a global and per-level basis. The agreement with each observer (Spearman’s correlation) was statistically significant (αs = 0.05, P <0.0001) and higher than that of at least one of the other observers in two out of three cases (ρOUR = 0.7594 versus ρObs3 = 0.7225; ρOUR = 0.8880 versus ρObs1 = 0.8017, ρObs3 = 0.7315). Based on paired-sample t-tests, these improvements were significant (P <0.001). CONCLUSIONS. Our automated system stratifies images by four tortuosity levels (discrete scale) matching or exceeding the accuracy of experienced observers. Of importance, the TP allows the assessment of tortuosity on a two-dimensional continuous scale, thus leading to a finer discrimination among images.

AB - PURPOSE. To assess the performance of a novel system for automated tortuosity estimation and interpretation. METHODS. A supervised strategy (driven by observers’ grading) was employed to automatically identify the combination of tortuosity measures (i.e., tortuosity representation) leading to the best agreement with the observers. We investigated 18 tortuosity measures including curvature and density of inflection points, computed at multiple spatial scales. To leverage tortuosity interpretation, we propose the tortuosity plane (TP) onto which each image is mapped. Experiments were carried out on 140 images of subbasal nerve plexus of the central cornea, covering four levels of tortuosity. Three experienced observers graded each image independently. RESULTS. The best tortuosity representation was the combination of mean curvature at spatial scales 2 and 5. These tortuosity measures were the axes of the proposed TP (interpretation). The system for tortuosity estimation revealed strong agreement with the observers on a global and per-level basis. The agreement with each observer (Spearman’s correlation) was statistically significant (αs = 0.05, P <0.0001) and higher than that of at least one of the other observers in two out of three cases (ρOUR = 0.7594 versus ρObs3 = 0.7225; ρOUR = 0.8880 versus ρObs1 = 0.8017, ρObs3 = 0.7315). Based on paired-sample t-tests, these improvements were significant (P <0.001). CONCLUSIONS. Our automated system stratifies images by four tortuosity levels (discrete scale) matching or exceeding the accuracy of experienced observers. Of importance, the TP allows the assessment of tortuosity on a two-dimensional continuous scale, thus leading to a finer discrimination among images.

KW - Confocal microscopy

KW - Corneal subbasal nerve plexus

KW - Tortuosity plane

UR - http://www.scopus.com/inward/record.url?scp=84960982174&partnerID=8YFLogxK

U2 - 10.1167/iovs.15-18513

DO - 10.1167/iovs.15-18513

M3 - Article

VL - 57

SP - 1132

EP - 1139

JO - Investigative Ophthalmology & Visual Science

JF - Investigative Ophthalmology & Visual Science

SN - 0146-0404

IS - 3

ER -