An Automatic Tool for Quantification of Nerve Fibers in Corneal Confocal Microscopy Images

Xin Chen, Jim Graham, Mohammad A Dabbah, Ioannis N Petropoulos, Mitra Tavakoli, Rayaz A Malik, Xin Chen, Jim Graham, Mohammad A Dabbah, Ioannis N Petropoulos, Mitra Tavakoli, Rayaz A Malik

Abstract

Objective: We describe and evaluate an automated software tool for nerve-fiber detection and quantification in corneal confocal microscopy (CCM) images, combining sensitive nerve- fiber detection with morphological descriptors.

Method: We have evaluated the tool for quantification of Diabetic Sensorimotor Polyneuropathy (DSPN) using both new and previously published morphological features. The evaluation used 888 images from 176 subjects (84 controls and 92 patients with type 1 diabetes). The patient group was further subdivided into those with ( n = 63) and without ( n = 29) DSPN.

Results: We achieve improved nerve- fiber detection over previous results (91.7% sensitivity and specificity in identifying nerve-fiber pixels). Automatic quantification of nerve morphology shows a high correlation with previously reported, manually measured, features. Receiver Operating Characteristic (ROC) analysis of both manual and automatic measurement regimes resulted in similar results in distinguishing patients with DSPN from those without: AUC of about 0.77 and 72% sensitivity-specificity at the equal error rate point.

Conclusion: Automated quantification of corneal nerves in CCM images provides a sensitive tool for identification of DSPN. Its performance is equivalent to manual quantification, while improving speed and repeatability.

Significance: CCM is a novel in vivo imaging modality that has the potential to be a noninvasive and objective image biomarker for peripheral neuropathy. Automatic quantification of nerve morphology is a major step forward in the early diagnosis and assessment of progression, and, in particular, for use in clinical trials to establish therapeutic benefit in diabetic and other peripheral neuropathies.

Figures

Fig. 1
Fig. 1
(a) Original CCM image. (b) Manually quantified CCM image. (c) Automatically quantified CCM image. Red lines represent main nerve fibres, blue lines are branches and green spots indicate branch points on the main nerve trunks. Refer to online coloured version.
Fig. 2
Fig. 2
(a) Original CCM image (b) Response image after nerve-fibre detection and denoising (c) Nerve-fibre skeleton with highlighted weak connection segments (d) Nerve-fibre skeleton after assessment of weak connections. (e) Automatically detected end points (hollow circles) and intersection points (solid circles). (f) Final detected nerve fibres.
Fig. 3
Fig. 3
(a) Original CCM image with a highlighted segment, a selection of orthogonal profile lines are indicated on the enlarged inset. Profiles are calculated at each pixel along the segment. (b) Average of all the profile lines along the whole fibre segment. (c) The symmetric profile of (b) is firstly calculated, and then normalised (Solid line). A Gaussian distribution is fitted for nerve-fibre width estimation (broken line). The final width equals 2.5 times the RMS width (σ) of the fitted Gaussian curve.
Fig. 4
Fig. 4
ROC curves for nerve-fibre detection on dataset 2, using DMNN (Dual Model, Neural Network), DMRF (Dual Model, Random Forest), DTNN (Dual-Tree Wavelet, neural Network) and DTRF (Dual-Tree Wavelet, Random Forest) respectively.
Fig. 5
Fig. 5
Boxplots of manually measured features for control, non-neuropathy and neuropathy groups (a) MCNFD (b) MCNFL (c) MCNBD.
Fig. 6
Fig. 6
Boxplots of automatically measured features for control, non-neuropathy and neuropathy groups in dataset 2 (a) ACNFD (b) ACNFL (c) ACNBD (d) ACNFA (e) ASDOH (f) ASDWH.

References

    1. Boulton AJ. Management of Diabetic Peripheral Neuropathy. Clinical Diabetes. 2005;23(1):9–15.
    1. Daousi C, MacFarlane IA, Woodward A, Nurmikko TJ, Bundred PE, Benbow SJ. Chronic painful peripheral neuropathy in an urban community: a controlled comparison of people with and without diabetes. Diabetic Medicine. 2004;21(9):976–982.
    1. Dyck PJ, Overland CJ, Low PA, Litchy WJ, Davies JL, O’Brien PC, Albers JW, Andersen H, Bolton CF, England JD, Klein CJ, Llewelyn JG, Mauermann ML, Russell JW, Singer W, Smith AG, Tesfaye S, Vella A C. v. N. T. Investigators. Signs and symptoms versus nerve conduction studies to diagnose diabetic sensorimotor polyneuropathy: CI vs. NPhys trial. Muscle Nerve. 2010;42(2):157–164.
    1. Dyck PJ, Albers JW, Wolfe J, Bolton CF, Walsh N, Klein CJ, Zafft AJ, Russell JW, Thomas K, Davies JL, Carter RE, Melton LJ, Litchy WJ C. v. N. T. Investigators. A trial of proficiency of nerve conduction: greater standardization still needed. Muscle nerve. 2013;48(3):369–374.
    1. Dyck PJ, Norell JE, Tritschler H, Schuette K, Samigullin R, Ziegler D, Bastyr EJ, Litchy WJ, O’Brien PC. Challenges in Design of Multicenter Trials: Endpoints Assessed Longitudinally for Change and Monotonicity. Diabetes Care. 2007;30:2619–2625.
    1. Tesfaye S, Boulton AJ, Dyck PJ, Freeman R, Horowitz M, Kempler P, Lauria G, Malik RA, Spallone V, Vinik A, Bernardi L, Valensi P on behalf of the Toronto Diabetic Neuropathy Expert Group. Diabetic neuropathies: Update on definitions, diagnostic criteria, estimation of severity, and treatments. Diabetes Care. 2010;33(10):2285–2293.
    1. Hossain P, Sachdev A, Malik RA. Early detection of diabetic peripheral neuropathy with corneal confocal microscopy. The Lancet. 2005;366(94):1340–1343.
    1. Pritchard N, Edwards K, Russell AW, Perkins BA, Malik RA, Efron N. Corneal confocal microscopy predicts 4-year incident peripheral neuropathy in type 1 diabetes. Diabetes Care. 2015;38(4):671–675.
    1. Brines M, Dunne AN, Velzen MV, Proto PL, Ostenson CG, Kirk RI, Petropoulos I, Javed S, Malik RA, Cerami A, Dahan A. ARA 290, a non-erythropoietic peptide engineered from erythropoiethin, improves metabolic control and neuropathic symptoms in patients with type 2 diabetes. Molecular Medicine. 2014;6
    1. Tavakoli M, Mitu-Pretorian M, Petropoulos IN, Fadavi H, Asghar O, Alam U, Ponirakis G, Jeziorska M, Marshall A, Efron N, Boulton AJ, Augustine T, Malik RA. Corneal confocal microscopy detects early nerve regeneration in diabetic neuropathy after simultaneous pancreas and kidney transplantation. Diabetes Care. 2013;62(1):254–260.
    1. Azmi S, Ferdousi M, Petropoulos IN, Ponirakis G, Fadavi H, Tavakoli M, Alam U, Jones W. Corneal confocal microscopy shows an improvement in small-fiber neuropathy in subjects with type 1 diabetes on continuous subcutaneous insulin infusion compared with multiple daily injection. Diabetes Care. 2015;38(1):e3–e4.
    1. Tavakoli M, Quattrini C, Abbott C, Kallinikos P, Marshall A, Finnigan J, Morgan P, Efron N, Boulton A, Malik R. Corneal Confocal Microscopy: A Novel Non-invasive Test to Diagnose and Stratify the Severity of Human Diabetic Neuropathy. Diabetes Care. 2010;33(8):1792–1797.
    1. Malik RA, Kallinikos P, Abbott CA, Schie CHMv, Morgan P, Efron N, Boulton AJM. Corneal confocal microscopy: a noninvasive surrogate of nerve fibre damage and repair in diabetic patients. Diabetologia. 2003;46(5):683–688.
    1. Dehghani C, Pritchard N, Edwards K, Vagenas D, Russell AW, Malik RA, Efron N. Morphometric stability of the corneal subbasal nerve plexus in healthy individuals: 1 3-year longitudinal study using corneal confocal microscopy. Invest Ophthalmol Visual Science. 2014;55(5):3195–3199.
    1. Petropoulos I, Manzoor T, Morgan P, Fadavi H, Asghar O, Alam U, Ponirakis G, Dabbah M, Chen X, Graham J, Tavakoli M, Malik R. Repeatability of In Vivo Corneal Confocal Microscopy to Quantify Corneal Nerve Morphology. Cornea. 2013;32(5):83–89.
    1. Niemeijer M, Staal JJ, Ginneken Bv, Loog M, Abramoff MD. Comparative study of retinal vessel segmentation methods on a new publicly available database. SPIE Medical Imaging. 2004;5370:648–656.
    1. Berks M, Chen Z, Astley S, Taylor C. Detecting and classifying linear structures in mammograms using random forests. IPMI 11 proceedings of the 22nd international conference on information processing in medical imaging; 2011. pp. 510–524.
    1. Scarpa F, Grisan E, Ruggeri A. Automatic Recognition of Corneal Nerve Structures in Images from Confocal Microscopy. Investigative Ophthalmology and Visual Science. 2008;49(11):4801–4807.
    1. Holmes T, Pellegrini M, Miller C, Epplin-Zapf T, Larkin S, Luccarelli S, Staurenghi G. Automated Software Analysis of Corneal Micrographs for Peripheral Neuropathy. Investigative Ophthalmology and Visual Science. 2010;51(9):4480–4491.
    1. Sindt CW, Lay B, Bouchard H, Kern JR. Rapid Image Evaluation System for Corneal In Vivo Confocal Microscopy. Cornea. 2013;32(4):460–465.
    1. Dabbah MA, Graham J, Petropoulos IN, Tavakoli M, Malik RA. Automatic analysis of diabetic peripheral neuropathy using multi-scale quantitative morphology of nerve fibres in corneal confocal microscopy imaging. Medical Image Analysis. 2011;15:738–747.
    1. Petropoulos IN, Alam U, Fadavi H, Marshal A, Asghar O, Dabbah MA, Chen X, Graham J, Ponikaris G, Boulton AJM, Tavakoli M, Malik RA. Rapid automated diagnosis of diabetic peripheral neuropathy with in vivo corneal confocal microscopy. Investigative Optics and Visual Science. 2014;55:2071–2078.
    1. Kingsbury NG. Complex wavelets for shift invariant analysis and filtering of signals. Journal of Applied and Computational Harmonic Analysis. 2001;10(3):234–253.
    1. Kotsiantis SB, Zaharakis ID, Pintelas PE. Machine learning: a review of classification and combining techniques. Artificial Intelligence Review. 2006;26(3):159–190.
    1. Meijer JWG, Smit AJ, Sonderen EV, Groothoff JW, Eisma WH, Links TP. Symptom scoring systems to diagnose distal polyneuropathy in diabetes: the Diabetic Neuropathy Symptom score. Diabetic Medicine. 2002;19(11):962–965.
    1. Young MJ, Boulton AJM, Macleod AF, Williams DRR, Sonksen PH. A multicentre study of the prevalence of diabetic peripheral neuropathy in the United Kingdom hospital clinic population. Diabetologia. 1993;36:150–154.
    1. Wallis K. Use of ranks in on-criterion variance analysis. Journal of the American Statistical Association. 1952;47(260):583–621.
    1. Holmes T, Pellegrini M, Miller C, Epplin-Zapf T, Larkin S, Luccarelli S, Staurengbi G. Automated Software Analysis of Corneal Micrographs for Peripheral Neuropathy. Investigative Ophthalmology and Visual Science. 2010;51(9):4480–4491.
    1. Tavakoli M, Marshall A, Thompson L, Kenny M, Waldek S, Efron N, Malik RA. Corneal confocal microscopy: a novel noninvasive means to diagnose neuropathy in patients with Fabry disease. Muscle Nerve. 2009 Dec;40(6):976–84.
    1. Tavakoli M, Marshall A, Pitceathly R, Fadavi H, Gow D, Roberts ME, Efron N, Boulton AJ, Malik RA. Corneal confocal microscopy: a novel means to detect nerve fibre damage in idiopathic small fibre neuropathy. Exp Neurol. 2010 May;223(1):245–50.
    1. Tavakoli M, Marshall A, Banka S, Petropoulos IN, Fadavi H, Kingston H, Malik RA. Corneal confocal microscopy detects small-fiber neuropathy in Charcot-Marie-Tooth disease type 1A patients. Muscle Nerve. 2012 Nov;46(5):698–704.
    1. van Velzen M, Heij L, Niesters M, Cerami A, Dunne A, Dahan A, Brines M. ARA 290 for treatment of small fiber neuropathy in sarcoidosis. Expert Opin Investig Drugs. 2014 Apr;23(4):541–50.
    1. Accmetrics.
    1. ENAgroup.
    1. Chen X, Graham J, Dabbah M, Petropoulos I, Ponirakis G, Asghar O, Alam U, Marshall A, Fadavi H, Ferdousi M, Azmi S, Tavakoli M, Efron N, Jeziorska M, Malik R. Small nerve fiber quantification in the diagnosis of diabetic sensorimotor polyneuropathy: comparing corneal confocal microscopy with intraepidermal nerve fiber density. Diabetes Care. 2015;38(6):1138–1144.

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe