CoChat
Sign Up
Cited by 155Ocular Surface and Contact LensRetinal Imaging and AnalysisAI in cancer detection

An artificial intelligence-based deep learning algorithm for the diagnosis of diabetic neuropathy using corneal confocal microscopy: a development and validation study

Open access
Williams, Bryan M., Borroni, Davide, Liu, Rongjun, Zhao, Yitian, Zhang, Jiong, Lim, Jonathan, Ma, Baikai, Romano, Vito +8 more·2020·Diabetologia
DOI 10.1007/s00125-019-05023-4PMC PMC6946763
Open this paper in CoChat — free accountOpen PDF

Abstract

Aims/hypothesis: Corneal confocal microscopy is a rapid non-invasive ophthalmic imaging technique that identifies peripheral and central neurodegenerative disease. Quantification of corneal sub-basal nerve plexus morphology, however, requires either time-consuming manual annotation or a less-sensitive automated image analysis approach. We aimed to develop and validate an artificial intelligence-based, deep learning algorithm for the quantification of nerve fibre properties relevant to the diagnosis of diabetic neuropathy and to compare it with a validated automated analysis program, ACCMetrics. Methods: Our deep learning algorithm, which employs a convolutional neural network with data augmentation, was developed for the automated quantification of the corneal sub-basal nerve plexus for the diagnosis of diabetic neuropathy. The algorithm was trained using a high-end graphics processor unit on 1698 corneal confocal microscopy images; for external validation, it was further tested on 2137 images. The algorithm was developed to identify total nerve fibre length, branch points, tail points, number and length of nerve segments, and fractal numbers. Sensitivity analyses were undertaken to determine the AUC for ACCMetrics and our algorithm for the diagnosis of diabetic neuropathy. Results: The intraclass correlation coefficients for our algorithm were superior to those for ACCMetrics for total corneal nerve fibre length (0.933 vs 0.825), mean length per segment (0.656 vs 0.325), number of branch points (0.891 vs 0.570), number of tail points (0.623 vs 0.257), number of nerve segments (0.878 vs 0.504) and fractals (0.927 vs 0.758). In addition, our proposed algorithm achieved an AUC of 0.83, specificity of 0.87 and sensitivity of 0.68 for the classification of participants without ( n = 90) and with ( n = 132) neuropathy (defined by the Toronto criteria). Conclusions/interpretation: These results demonstrated that our deep learning algorithm provides rapid and excellent localisation performance for the quantification of corneal nerve biomarkers. This model has potential for adoption into clinical screening programmes for diabetic neuropathy. Data availability: The publicly shared cornea nerve dataset (dataset 1) is available at http://bioimlab.dei.unipd.it/Corneal%20Nerve%20Tortuosity%20Data%20Set.htm and http://bioimlab.dei.unipd.it/Corneal%20Nerve%20Data%20Set.htm .

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s00125-019-05023-4

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Previous studies explored the development of AI systems to identify diabetic neuropathy based on EHRs or corneal confocal microscopy images, with AUCs ranging from 0.83 to 0.95.

    “For neuropathy screening, previous studies explored the development of AI systems to identify diabetic neuropathy based on EHRs116 or corneal confocal microscopy images,117,118,119 with AUCs ranging from 0.83 to 0.95.”

    From Artificial intelligence in diabetes management: Advancements, opportunities, and challenges (2023) · cites this paper as [117]

  • Williams et al. reported that a CNN using corneal confocal microscopy images to identify diabetic peripheral neuropathy achieved an AUC of 0.83, sensitivity of 67.7%, and specificity of 86.7%.

    “the AUC of the system was 0.83, sensitivity was 67.7%, and specificity was 86.7%”

    From Artificial intelligence in diabetes management: Advancements, opportunities, and challenges (2023) · cites this paper as Williams et al.117

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 44

  1. [1]Tan H Yang M Wu Z Rapid screening method for Schistosoma japonicum infection using questionnaires in flood area of the People’s Republic of China Acta Trop 2004 90 1 1 9 14739016
  2. [2]Lauria G Cornblath D Johansson O EFNS guidelines on the use of skin biopsy in the diagnosis of peripheral neuropathy Eur J Neurol 2005 12 10 747 758 16190912
  3. [4]Quattrini C Tavakoli M Jeziorska M Surrogate markers of small fiber damage in human diabetic neuropathy Diabetes 2007 56 8 2148 2154 17513704
  4. [5]Dehghani C Pritchard N Edwards K Morphometric stability of the corneal subbasal nerve plexus in healthy individuals: a 3-year longitudinal study using corneal confocal microscopy Invest Ophth Vis Sci 2014 55 5 3195 3199 24764058
  5. [6]Sivaskandarajah GA Halpern EM Lovblom LE Structure-function relationship between corneal nerves and conventional small-fiber tests in type 1 diabetes Diabetes Care 2013 36 9 2748 2755 23579181 PMC3747893
  6. [7]Tavakoli M Quattrini C Abbott C Corneal confocal microscopy: a novel noninvasive test to diagnose and stratify the severity of human diabetic neuropathy Diabetes Care 2010 33 8 1792 1797 20435796 PMC2909064
  7. [8]Kemp HI Petropoulos IN Rice AS Use of corneal confocal microscopy to evaluate small nerve fibers in patients with human immunodeficiency virus JAMA Ophthalmol 2017 135 7 795 800 28594979 PMC6583030
  8. [9]Ferdousi M Azmi S Petropoulos IN Corneal confocal microscopy detects small fibre neuropathy in patients with upper gastrointestinal cancer and nerve regeneration in chemotherapy induced peripheral neuropathy PloS One 2015 10 10 e0139394 26430773 PMC4592260
  9. [10]Tavakoli M Marshall A Thompson L Corneal confocal microscopy: a novel noninvasive means to diagnose neuropathy in patients with Fabry disease Muscle Nerve 2009 40 6 976 984 19902546
  10. [11]Tavakoli M Marshall A Pitceathly R Corneal confocal microscopy: a novel means to detect nerve fibre damage in idiopathic small fibre neuropathy Exp Neurol 2010 223 1 245 250 19748505 PMC2938826
  11. [12]Petropoulos IN Alam U Fadavi H Corneal nerve loss detected with corneal confocal microscopy is symmetrical and related to the severity of diabetic polyneuropathy Diabetes Care 2013 36 11 3646 3651 23877983 PMC3816900
  12. [13]Petropoulos IN Manzoor T Morgan P Repeatability of in vivo corneal confocal microscopy to quantify corneal nerve morphology Cornea 2013 32 5 e83 e89 23172119
  13. [14]Petropoulos IN Alam U Fadavi H Rapid automated diagnosis of diabetic peripheral neuropathy with in vivo corneal confocal microscopy Invest Ophth Vis Sci 2014 55 4 2071 2078 PMC3979234 24569580
  14. [15]Alam U Jeziorska M Petropoulos IN Diagnostic utility of corneal confocal microscopy and intra-epidermal nerve fibre density in diabetic neuropathy PloS One 2017 12 7 e0180175 28719619 PMC5515394
  15. [16]Chen X Graham J Dabbah MA 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 25795415 PMC4439535
  16. [17]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 25573881
  17. [18]Tavakoli M Mitu-Pretorian M Petropoulos IN Corneal confocal microscopy detects early nerve regeneration in diabetic neuropathy after simultaneous pancreas and kidney transplantation Diabetes 2013 62 1 254 260 23002037 PMC3526062
  18. [19]Ziegler D Papanas N Zhivov A Early detection of nerve fiber loss by corneal confocal microscopy and skin biopsy in recently diagnosed type 2 diabetes Diabetes 2014 63 7 2454 2463 24574045
  19. [20]Brines M Culver DA Ferdousi M Corneal nerve fiber size adds utility to the diagnosis and assessment of therapeutic response in patients with small fiber neuropathy Sci Rep-UK 2018 8 1 4734 PMC5856845 29549285
  20. [21]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 Med Image Anal 2011 15 5 738 747 21719344
  21. [22]Dabbah MA Graham J Petropoulos I Tavakoli M Malik RA Jiang T Navab N Pluim JPW Viergever MA Dual-model automatic detection of nerve-fibres in corneal confocal microscopy images Medical Image Computing and Computer-Assisted Intervention (MICCAI). Lecture Notes in Computer Science 2010 Berlin, Heidelberg Springer 300 307 PMC3066470 20879244
  22. [23]Kim J Markoulli M Automatic analysis of corneal nerves imaged using in vivo confocal microscopy Clin Exp Optom 2018 101 2 147 161 29193361
  23. [24]Chen X Graham J Dabbah MA Petropoulos IN Tavakoli M Malik RA An automatic tool for quantification of nerve fibers in corneal confocal microscopy images IEEE Trans Biomed Eng 2017 64 4 786 794 27295646 PMC5512547
  24. [25]LeCun Y Bengio Y Hinton G Deep learning Nature 2015 521 7553 436 26017442
  25. [26]Hubel DH Wiesel TN Receptive fields and functional architecture of monkey striate cortex J Physiol 1968 195 1 215 243 4966457 PMC1557912
  26. [27]Shen D Wu G Suk H-I Deep learning in medical image analysis Annu Rev Biomed Eng 2017 19 221 248 28301734 PMC5479722
  27. [28]Scarpa F Zheng X Ohashi Y Ruggeri A Automatic evaluation of corneal nerve tortuosity in images from in vivo confocal microscopy Invest Ophth Vis Sci 2011 52 9 6404 6408 21775658
  28. [29]Scarpa F Grisan E Ruggeri A Automatic recognition of corneal nerve structures in images from confocal microscopy Invest Ophth Vis Sci 2008 49 11 4801 4807 18614801
  29. [31]Marfurt Carl F. Cox Jeremiah Deek Sylvia Dvorscak Lauren Anatomy of the human corneal innervation Experimental Eye Research 2010 90 4 478 492 20036654
  30. [32]Borroni D, Beech M, Williams B et al (2018) Building a validated in vivo confocal microscopy (IVCM) dataset for the study of corneal nerves. Invest Ophth Vis Sci 59(9):5719
  31. [33]Matsumoto M Nishimura T Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator ACM Transactions on Modeling and Computer Simulation (TOMACS) 1998 8 1 3 30
  32. [35]Brunner M Romano V Steger B Imaging of corneal neovascularization: optical coherence tomography angiography and fluorescence angiography Invest Ophth Vis Sci 2018 59 3 1263 1269 29625447
  33. [37]Youden WJ Index for rating diagnostic tests Cancer 1950 3 1 32 35 15405679
  34. [38]Chen X Graham J Petropoulos IN Corneal nerve fractal dimension: a novel corneal nerve metric for the diagnosis of diabetic sensorimotor polyneuropathy Invest Ophth Vis Sci 2018 59 2 1113 1118 PMC5830988 29490348
  35. [39]Bianciardi G Latronico M Traversi C Decreased geometric complexity of corneal nerve fibers distribution in Sjogren’s syndrome patients Int J Ophthalmic Pathol Res 2015 4 2 26499877
  36. [40]Perkins BA Lovblom LE Bril V Corneal confocal microscopy for identification of diabetic sensorimotor polyneuropathy: a pooled multinational consortium study Diabetologia 2018 61 8 1856 1861 29869146 PMC6061173
  37. [41]Azmi S Jeziorska M Ferdousi M Early nerve fibre regeneration in individuals with type 1 diabetes after simultaneous pancreas and kidney transplantation Diabetologia 2019 62 8 1478 1487 31175373 PMC6647173
  38. [42]Baraz Shahram Zarea Kourosh Shahbazian Hajie Latifi Seyed Comparison of the accuracy of monofilament testing at various points of feet in peripheral diabetic neuropathy screening Journal of Diabetes & Metabolic Disorders 2014 13 1 19 24472435 PMC3922886
  39. [43]Qi H, Borroni D, Liu R et al (2018) Automated detection of corneal nerves using deep learning. Invest Ophth Vis Sci 59(9):5721
  40. [44]Oakley JD, Russakoff DB, Weinberg R et al (2018) Automated analysis of in vivo confocal microscopy corneal images using deep learning. Investigative Ophthalmology & Visual Science 59(9):1799
  41. [45]Zhang J Bekkers E Chen D Reconnection of interrupted curvilinear structures via cortically inspired completion for ophthalmologic images IEEE Trans Biomed Eng 2018 65 5 1151 1165 29683430 PMC6880863
  42. [48]Lauria G Hsieh ST Johansson O European Federation of Neurological Societies/Peripheral Nerve Society Guideline on the use of skin biopsy in the diagnosis of small fiber neuropathy. Report of a joint task force of the European Federation of Neurological Societies and the Peripheral Nerve Society Eur J Neurol 2010 17 7 903 912 20642627
  43. [49]Alam U Riley DR Jugdey RS Diabetic neuropathy and gait: a review Diabetes Ther 2017 8 6 1253 1264 28864841 PMC5688977
  44. [50]Culver Daniel A. Dahan Albert Bajorunas Daiva Jeziorska Maria van Velzen Monique Aarts Leon P. H. J. Tavee Jinny Tannemaat Martijn R. Dunne Ann N. Kirk Rita I. Petropoulos Ioannis N. Cerami Anthony Malik Rayaz A. Brines Michael Cibinetide Improves Corneal Nerve Fiber Abundance in Patients With Sarcoidosis-Associated Small Nerve Fiber Loss and Neuropathic Pain Investigative Opthalmology & Visual Science 2017 58 6 BIO52 28475703

Cited by

Sorted by citations

Authors
Williams, B. M., Borroni, D., Liu, R., Zhao, Y., Zhang, J., Lim, J., Ma, B., Romano, V., Qi, H., Ferdousi, M., Petropoulos, I. N., Ponirakis, G., Kaye, S., Malik, R. A., Alam, U., & Zheng, Y.
Affiliations
  • University of Liverpool (GB)
  • Royal Liverpool University Hospital (GB)
  • Peking University Third Hospital (CN)
  • Chinese Academy of Sciences (CN)
  • University of Southern California (US)
  • Aintree University Hospital (GB)
  • Weill Cornell Medical College in Qatar (QA)
Corresponding author
  • Alam, Uazman
  • Zheng, Yalin
ORCID
Venue
Diabetologia
Publisher
Springer Science and Business Media LLC
Published
2019-11-12
Volume
63
Issue
2
Pages
419-430
ISSN
  • 0012-186X (ISSN-L)
  • 1432-0428
DOI
10.1007/s00125-019-05023-4
PMC
PMC6946763
OpenAlex
W2988620852
Cited by
155
References
6
Citations by year
2026: 13 · 2025: 17 · 2024: 30 · 2023: 24 · 2022: 27 · 2021: 30 · 2020: 14
FWCI
16.35
Type
journal article
Language
en
Open access
Licence
Locations
  • Diabetologia (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Research Explorer (The University of Manchester) (publishedVersion, other-oa)
  • Lancaster EPrints (Lancaster University) (submittedVersion)
  • Ningbo Institute of Materials Technology and Engineering, CAS Institutional Repository (submittedVersion)
  • Institutional Research Information System (Università degli Studi di Brescia) (submittedVersion, other-oa)
Funders
Nvidia
Topics
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Ocular Surface and Contact Lens
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
Keywords
diabetic neuropathy, corneal confocal microscopy, subbasal nerve plexus, deep learning, convolutional neural networks, automated image analysis, fractal analysis, diabetic neuropathy screening, non-invasive diagnosis, external validation, sensitivity and specificity, data augmentation
MeSH terms
Deep Learning, Algorithms, Artificial Intelligence, Cornea, Diabetes Mellitus, Type 1, Diabetic Neuropathies, Humans, Nerve Fibers, Microscopy, Confocal, Neurodegenerative Diseases

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review