Dataset Information

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

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.

SUBMITTER: Preston FG

PROVIDER: S-EPMC8803718 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Aims/hypothesisCorneal 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.MethodsOur 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.ResultsThe 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/interpretationThese 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 availabilityThe 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.

Project description:IntroductionThe assessment of the corneal nerve fibre plexus with corneal confocal microscopy (CCM) is an upcoming but still experimental method in the diagnosis of early stage diabetic peripheral neuropathy (DPN). Using an innovative imaging technique-Heidelberg Retina Tomograph equipped with the Rostock Cornea Module (HRT-RCM) and EyeGuidance module (EG)-we were able to look at greater areas of subbasal nerve plexus (SNP) in order to increase the diagnostic accuracy. The aim of our study was to evaluate the usefulness of EG instead of single image analysis in diagnosis of early stage DPN.MethodsThis prospective study was performed on 60 patients with type 2 diabetes mellitus, classified equally into two subgroups based on neuropathy deficient score (NDS): patients without DPN (group 1) or with mild DPN (group 2). The following parameters were analysed in the two subgroups: corneal nerve fibre length (CNFL; mm/mm2), corneal nerve fibre density (CNFD; no./mm2), corneal nerve branch density (CNBD; no./mm2). Furthermore, we compared the data calculated with the novel mosaic, EG-based method with those received from single image analysis using different quantification tools.ResultsUsing EG we did not find a significant difference between group 1 and group 2: CNFL (16.81 ± 5.87 mm/mm2 vs. 17.19 ± 7.19 mm/mm2, p = 0.895), CNFD (254.05 ± 115.36 no./mm2 vs. 265.91 ± 161.63 no./mm2, p = 0.732) and CNBD (102.68 ± 62.28 no./mm2 vs. 115.38 ± 96.91 no./mm2, p = 0.541). No significant difference between the EG method of analysing the SNP and the single image analysis of 10 images per patient was detected.ConclusionOn the basis of our results it was not possible to differentiate between early stages of large nerve fibre DPN in patients with type 2 diabetes mellitus via SNP analysis. To improve sensitivity and specificity of this method newer technologies are under current evaluation.Trial registrationClinicalTrials.gov Identifier NCT05326958.