Artificial Intelligence–Based Classification of Diabetic Peripheral Neuropathy From Corneal Confocal Microscopy Images

AbstractThis randomized controlled study used corneal confocal microscopy (CCM) to compare the efficacy of Mecobalamin intramuscular injections vs oral tablets in treating mild to moderate diabetic peripheral neuropathy (DPN) by detecting early nerve fiber repair. Enrolled patients were randomized approximately 1:1 to receive Mecobalamin intramuscular injections (0.5 mg/day, 3 times/week) or Mecobalamin oral tablets (1.5 mg/day) for 8 weeks. Primary outcome was change of inferior whorl length (IWL) from baseline. Secondary outcomes included changes of corneal nerve fibre length (CNFL), corneal nerve fibre density (CNFD), corneal nerve branch density (CNBD) and the Survey of Autonomic Symptoms (SAS). 15 (93.75%) patients in the injection group and 17 (89.47%) patients in the tablet group completed the study. The injection treatment significantly improved patients’ IWL from baseline (21.64 ± 3.00 mm/mm2 vs 17.64 ± 4.83 mm/mm2, P < 0.01) while the tablet treatment didn’t. Additionally, the injection treatment led to significantly improved CNFL, CNBD and SAS from baseline (all P < 0.05) while the tablet treatment did not. No patient experienced any adverse events. In conclusion, CCM is sensitive enough to detect the superior efficacy of 8-week Mecobalamin intramuscular injection treatment for DPN compared to the oral tablet treatment.ClinicalTrials.gov registration number: NCT04372316 (30/04/2020).

Download Full-text

Rapid Automated Diagnosis of Diabetic Peripheral Neuropathy With In Vivo Corneal Confocal Microscopy

Investigative Opthalmology & Visual Science ◽

10.1167/iovs.13-13787 ◽

2014 ◽

Vol 55 (4) ◽

pp. 2071 ◽

Cited By ~ 106

Author(s):

Ioannis N. Petropoulos ◽

Uazman Alam ◽

Hassan Fadavi ◽

Andrew Marshall ◽

Omar Asghar ◽

...

Keyword(s):

Peripheral Neuropathy ◽

Confocal Microscopy ◽

Diabetic Peripheral Neuropathy ◽

Automated Diagnosis ◽

Corneal Confocal Microscopy

Download Full-text

Corneal confocal microscopy for assessment of diabetic peripheral neuropathy: a meta-analysis

British Journal of Ophthalmology ◽

10.1136/bjophthalmol-2014-306038 ◽

2015 ◽

Vol 100 (1) ◽

pp. 9-14 ◽

Cited By ~ 48

Author(s):

Min-Shan Jiang ◽

Ying Yuan ◽

Zhao-Xiang Gu ◽

Song-Lin Zhuang

Keyword(s):

Peripheral Neuropathy ◽

Confocal Microscopy ◽

Diabetic Peripheral Neuropathy ◽

Meta Analysis ◽

Corneal Confocal Microscopy

Download Full-text

Automatic analysis of diabetic peripheral neuropathy using multi-scale quantitative morphology of nerve fibres in corneal confocal microscopy imaging

Medical Image Analysis ◽

10.1016/j.media.2011.05.016 ◽

2011 ◽

Vol 15 (5) ◽

pp. 738-747 ◽

Cited By ~ 118

Author(s):

M.A. Dabbah ◽

J. Graham ◽

I.N. Petropoulos ◽

M. Tavakoli ◽

R.A. Malik

Keyword(s):

Peripheral Neuropathy ◽

Confocal Microscopy ◽

Diabetic Peripheral Neuropathy ◽

Automatic Analysis ◽

Quantitative Morphology ◽

Nerve Fibres ◽

Microscopy Imaging ◽

Multi Scale ◽

Corneal Confocal Microscopy ◽

Confocal Microscopy Imaging

Download Full-text

Corneal confocal microscopy as a non-invasive test to assess diabetic peripheral neuropathy

Diabetes Research and Clinical Practice ◽

10.1016/j.diabres.2017.11.026 ◽

2018 ◽

Vol 136 ◽

pp. 85-92 ◽

Cited By ~ 5

Author(s):

Qian Xiong ◽

Bin Lu ◽

Hong-Ying Ye ◽

Si-Ying Liu ◽

Hang-Ping Zheng ◽

...

Keyword(s):

Peripheral Neuropathy ◽

Confocal Microscopy ◽

Diabetic Peripheral Neuropathy ◽

Non Invasive ◽

Invasive Test ◽

Corneal Confocal Microscopy

Download Full-text

Corneal Confocal Microscopy – A Novel, Noninvasive Method to Assess Diabetic Peripheral Neuropathy

Romanian Journal of Diabetes Nutrition and Metabolic Diseases ◽

10.2478/rjdnmd-2014-0039 ◽

2014 ◽

Vol 21 (4) ◽

pp. 319-326 ◽

Cited By ~ 1

Author(s):

Georgeta Inceu ◽

Horea Demea ◽

Ioan Andrei Veresiu

Keyword(s):

Peripheral Neuropathy ◽

Confocal Microscopy ◽

Diabetic Neuropathy ◽

Diabetic Peripheral Neuropathy ◽

Diabetic Patients ◽

Noninvasive Method ◽

Anthropometric Parameters ◽

Perception Threshold ◽

Peripheral Diabetic Neuropathy ◽

Corneal Confocal Microscopy

AbstractBackground and aims. This article aims to compare corneal confocal microscopy (CCM) with acknowledged tests of diabetic peripheral neuropathy (DPN), to assess corneal nerve morphology using CCM in diabetic patients, and to underline possible correlations between clinical and biological parameters, diabetes duration and DPN severity. Material and methods. A total of 90 patients with type 2 diabetes were included in the study for whom we measured anthropometric parameters and we performed laboratory measurements (tests). The patients were assessed for diabetic peripheral neuropathy using Semmes-Weinstein Monofilament Testing (SWMT), Rapid-Current Perception Threshold (R-CPT) measurements using the Neurometer®, and CCM. We stratified the patients according to DPN severity, based on four parameters extracted after image analysis. Results. A higher percentage of patients were diagnosed with DPN using CCM (88.8%), compared with SWMT and R-CPT measurement (17.8% and 40% respectively). The incidence of DPN detected with CCM was considerable in patients with normal protective sensation and with normal R-CPT values. Conclusions. Our study showed that corneal confocal microscopy is a useful noninvasive method for diabetic neuropathy assessement in early stages. It was proven to directly quantify small fiber pathology, and to stratify neuropathic severity, and therefore can be used as a new, reliable tool in the diagnosis, clinical evaluation, and follow-up of peripheral diabetic neuropathy.

Download Full-text

Artificial intelligence utilising corneal confocal microscopy for the diagnosis of peripheral neuropathy in diabetes mellitus and prediabetes

Diabetologia ◽

10.1007/s00125-021-05617-x ◽

2021 ◽

Author(s):

Frank G. Preston ◽

Yanda Meng ◽

Jamie Burgess ◽

Maryam Ferdousi ◽

Shazli Azmi ◽

...

Keyword(s):

Artificial Intelligence ◽

Peripheral Neuropathy ◽

Confocal Microscopy ◽

Large Scale ◽

Data Augmentation ◽

Learning Algorithm ◽

Deep Learning Algorithm ◽

Corneal Confocal Microscopy ◽

Corneal Nerves ◽

Corneal Nerve

Abstract Aims/hypothesis We aimed to develop an artificial intelligence (AI)-based deep learning algorithm (DLA) applying attribution methods without image segmentation to corneal confocal microscopy images and to accurately classify peripheral neuropathy (or lack of). Methods The AI-based DLA utilised convolutional neural networks with data augmentation to increase the algorithm’s generalisability. The algorithm was trained using a high-end graphics processor for 300 epochs on 329 corneal nerve images and tested on 40 images (1 image/participant). Participants consisted of healthy volunteer (HV) participants (n = 90) and participants with type 1 diabetes (n = 88), type 2 diabetes (n = 141) and prediabetes (n = 50) (defined as impaired fasting glucose, impaired glucose tolerance or a combination of both), and were classified into HV, those without neuropathy (PN−) (n = 149) and those with neuropathy (PN+) (n = 130). For the AI-based DLA, a modified residual neural network called ResNet-50 was developed and used to extract features from images and perform classification. The algorithm was tested on 40 participants (15 HV, 13 PN−, 12 PN+). Attribution methods gradient-weighted class activation mapping (Grad-CAM), Guided Grad-CAM and occlusion sensitivity displayed the areas within the image that had the greatest impact on the decision of the algorithm. Results The results were as follows: HV: recall of 1.0 (95% CI 1.0, 1.0), precision of 0.83 (95% CI 0.65, 1.0), F1-score of 0.91 (95% CI 0.79, 1.0); PN−: recall of 0.85 (95% CI 0.62, 1.0), precision of 0.92 (95% CI 0.73, 1.0), F1-score of 0.88 (95% CI 0.71, 1.0); PN+: recall of 0.83 (95% CI 0.58, 1.0), precision of 1.0 (95% CI 1.0, 1.0), F1-score of 0.91 (95% CI 0.74, 1.0). The features displayed by the attribution methods demonstrated more corneal nerves in HV, a reduction in corneal nerves for PN− and an absence of corneal nerves for PN+ images. Conclusions/interpretation We demonstrate promising results in the rapid classification of peripheral neuropathy using a single corneal image. A large-scale multicentre validation study is required to assess the utility of AI-based DLA in screening and diagnostic programmes for diabetic neuropathy. Graphical abstract

Download Full-text