Rapid automated diagnosis of diabetic peripheral neuropathy with in vivo corneal confocal microscopy

Ioannis N. Petropoulos, Uazman Alam, Hassan Fadavi, Andrew Marshall, Omar Asghar, Mohammad A. Dabbah, Xin Chen, James Graham, Georgios Ponirakis, Andrew J M Boulton, Mitra Tavakoli, Rayaz Malik

Research output: Contribution to journalArticle

93 Citations (Scopus)

Abstract

Purpose. To assess the diagnostic validity of a fully automated image analysis algorithm of in vivo confocal microscopy images in quantifying corneal subbasal nerves to diagnose diabetic neuropathy. Methods. One hundred eighty-six patients with type 1 and type 2 diabetes mellitus (T1/ T2DM) and 55 age-matched controls underwent assessment of neuropathy and bilateral in vivo corneal confocal microscopy (IVCCM). Corneal nerve fiber density (CNFD), branch density (CNBD), and length (CNFL) were quantified with expert, manual, and fully-automated analysis. The areas under the curve (AUC), odds ratios (OR), and optimal thresholds to rule out neuropathy were estimated for both analysis methods. Results. Neuropathy was detected in 53% of patients with diabetes. A significant reduction in manual and automated CNBD (P < 0.001) and CNFD (P < 0.0001), and CNFL (P < 0.0001) occurred with increasing neuropathic severity. Manual and automated analysis methods were highly correlated for CNFD (r = 0.9, P < 0.0001), CNFL (r = 0.89, P < 0.0001), and CNBD (r = 0.75, P < 0.0001). Manual CNFD and automated CNFL were associated with the highest AUC, sensitivity/specificity and OR to rule out neuropathy. Conclusions. Diabetic peripheral neuropathy is associated with significant corneal nerve loss detected with IVCCM. Fully automated corneal nerve quantification provides an objective and reproducible means to detect human diabetic neuropathy.

Original languageEnglish
Pages (from-to)2062-2070
Number of pages9
JournalInvestigative Ophthalmology and Visual Science
Volume55
Issue number4
DOIs
Publication statusPublished - 3 Apr 2014
Externally publishedYes

Fingerprint

Diabetic Neuropathies
Peripheral Nervous System Diseases
Nerve Fibers
Confocal Microscopy
Area Under Curve
Odds Ratio
Type 1 Diabetes Mellitus
Type 2 Diabetes Mellitus
Sensitivity and Specificity

Keywords

  • Corneal confocal microscopy
  • Diabetes
  • Diabetic neuropathy

ASJC Scopus subject areas

  • Ophthalmology
  • Sensory Systems
  • Cellular and Molecular Neuroscience

Cite this

Rapid automated diagnosis of diabetic peripheral neuropathy with in vivo corneal confocal microscopy. / Petropoulos, Ioannis N.; Alam, Uazman; Fadavi, Hassan; Marshall, Andrew; Asghar, Omar; Dabbah, Mohammad A.; Chen, Xin; Graham, James; Ponirakis, Georgios; Boulton, Andrew J M; Tavakoli, Mitra; Malik, Rayaz.

In: Investigative Ophthalmology and Visual Science, Vol. 55, No. 4, 03.04.2014, p. 2062-2070.

Research output: Contribution to journalArticle

Petropoulos, IN, Alam, U, Fadavi, H, Marshall, A, Asghar, O, Dabbah, MA, Chen, X, Graham, J, Ponirakis, G, Boulton, AJM, Tavakoli, M & Malik, R 2014, 'Rapid automated diagnosis of diabetic peripheral neuropathy with in vivo corneal confocal microscopy', Investigative Ophthalmology and Visual Science, vol. 55, no. 4, pp. 2062-2070. https://doi.org/10.1167/iovs.13-13787
Petropoulos, Ioannis N. ; Alam, Uazman ; Fadavi, Hassan ; Marshall, Andrew ; Asghar, Omar ; Dabbah, Mohammad A. ; Chen, Xin ; Graham, James ; Ponirakis, Georgios ; Boulton, Andrew J M ; Tavakoli, Mitra ; Malik, Rayaz. / Rapid automated diagnosis of diabetic peripheral neuropathy with in vivo corneal confocal microscopy. In: Investigative Ophthalmology and Visual Science. 2014 ; Vol. 55, No. 4. pp. 2062-2070.
@article{ee876a250d9949738473d5dc4157651c,
title = "Rapid automated diagnosis of diabetic peripheral neuropathy with in vivo corneal confocal microscopy",
abstract = "Purpose. To assess the diagnostic validity of a fully automated image analysis algorithm of in vivo confocal microscopy images in quantifying corneal subbasal nerves to diagnose diabetic neuropathy. Methods. One hundred eighty-six patients with type 1 and type 2 diabetes mellitus (T1/ T2DM) and 55 age-matched controls underwent assessment of neuropathy and bilateral in vivo corneal confocal microscopy (IVCCM). Corneal nerve fiber density (CNFD), branch density (CNBD), and length (CNFL) were quantified with expert, manual, and fully-automated analysis. The areas under the curve (AUC), odds ratios (OR), and optimal thresholds to rule out neuropathy were estimated for both analysis methods. Results. Neuropathy was detected in 53{\%} of patients with diabetes. A significant reduction in manual and automated CNBD (P < 0.001) and CNFD (P < 0.0001), and CNFL (P < 0.0001) occurred with increasing neuropathic severity. Manual and automated analysis methods were highly correlated for CNFD (r = 0.9, P < 0.0001), CNFL (r = 0.89, P < 0.0001), and CNBD (r = 0.75, P < 0.0001). Manual CNFD and automated CNFL were associated with the highest AUC, sensitivity/specificity and OR to rule out neuropathy. Conclusions. Diabetic peripheral neuropathy is associated with significant corneal nerve loss detected with IVCCM. Fully automated corneal nerve quantification provides an objective and reproducible means to detect human diabetic neuropathy.",
keywords = "Corneal confocal microscopy, Diabetes, Diabetic neuropathy",
author = "Petropoulos, {Ioannis N.} and Uazman Alam and Hassan Fadavi and Andrew Marshall and Omar Asghar and Dabbah, {Mohammad A.} and Xin Chen and James Graham and Georgios Ponirakis and Boulton, {Andrew J M} and Mitra Tavakoli and Rayaz Malik",
year = "2014",
month = "4",
day = "3",
doi = "10.1167/iovs.13-13787",
language = "English",
volume = "55",
pages = "2062--2070",
journal = "Investigative Ophthalmology and Visual Science",
issn = "0146-0404",
publisher = "Association for Research in Vision and Ophthalmology Inc.",
number = "4",

}

TY - JOUR

T1 - Rapid automated diagnosis of diabetic peripheral neuropathy with in vivo corneal confocal microscopy

AU - Petropoulos, Ioannis N.

AU - Alam, Uazman

AU - Fadavi, Hassan

AU - Marshall, Andrew

AU - Asghar, Omar

AU - Dabbah, Mohammad A.

AU - Chen, Xin

AU - Graham, James

AU - Ponirakis, Georgios

AU - Boulton, Andrew J M

AU - Tavakoli, Mitra

AU - Malik, Rayaz

PY - 2014/4/3

Y1 - 2014/4/3

N2 - Purpose. To assess the diagnostic validity of a fully automated image analysis algorithm of in vivo confocal microscopy images in quantifying corneal subbasal nerves to diagnose diabetic neuropathy. Methods. One hundred eighty-six patients with type 1 and type 2 diabetes mellitus (T1/ T2DM) and 55 age-matched controls underwent assessment of neuropathy and bilateral in vivo corneal confocal microscopy (IVCCM). Corneal nerve fiber density (CNFD), branch density (CNBD), and length (CNFL) were quantified with expert, manual, and fully-automated analysis. The areas under the curve (AUC), odds ratios (OR), and optimal thresholds to rule out neuropathy were estimated for both analysis methods. Results. Neuropathy was detected in 53% of patients with diabetes. A significant reduction in manual and automated CNBD (P < 0.001) and CNFD (P < 0.0001), and CNFL (P < 0.0001) occurred with increasing neuropathic severity. Manual and automated analysis methods were highly correlated for CNFD (r = 0.9, P < 0.0001), CNFL (r = 0.89, P < 0.0001), and CNBD (r = 0.75, P < 0.0001). Manual CNFD and automated CNFL were associated with the highest AUC, sensitivity/specificity and OR to rule out neuropathy. Conclusions. Diabetic peripheral neuropathy is associated with significant corneal nerve loss detected with IVCCM. Fully automated corneal nerve quantification provides an objective and reproducible means to detect human diabetic neuropathy.

AB - Purpose. To assess the diagnostic validity of a fully automated image analysis algorithm of in vivo confocal microscopy images in quantifying corneal subbasal nerves to diagnose diabetic neuropathy. Methods. One hundred eighty-six patients with type 1 and type 2 diabetes mellitus (T1/ T2DM) and 55 age-matched controls underwent assessment of neuropathy and bilateral in vivo corneal confocal microscopy (IVCCM). Corneal nerve fiber density (CNFD), branch density (CNBD), and length (CNFL) were quantified with expert, manual, and fully-automated analysis. The areas under the curve (AUC), odds ratios (OR), and optimal thresholds to rule out neuropathy were estimated for both analysis methods. Results. Neuropathy was detected in 53% of patients with diabetes. A significant reduction in manual and automated CNBD (P < 0.001) and CNFD (P < 0.0001), and CNFL (P < 0.0001) occurred with increasing neuropathic severity. Manual and automated analysis methods were highly correlated for CNFD (r = 0.9, P < 0.0001), CNFL (r = 0.89, P < 0.0001), and CNBD (r = 0.75, P < 0.0001). Manual CNFD and automated CNFL were associated with the highest AUC, sensitivity/specificity and OR to rule out neuropathy. Conclusions. Diabetic peripheral neuropathy is associated with significant corneal nerve loss detected with IVCCM. Fully automated corneal nerve quantification provides an objective and reproducible means to detect human diabetic neuropathy.

KW - Corneal confocal microscopy

KW - Diabetes

KW - Diabetic neuropathy

UR - http://www.scopus.com/inward/record.url?scp=84898714478&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898714478&partnerID=8YFLogxK

U2 - 10.1167/iovs.13-13787

DO - 10.1167/iovs.13-13787

M3 - Article

C2 - 24569580

AN - SCOPUS:84898714478

VL - 55

SP - 2062

EP - 2070

JO - Investigative Ophthalmology and Visual Science

JF - Investigative Ophthalmology and Visual Science

SN - 0146-0404

IS - 4

ER -