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

Salahouddin, Tooba; Petropoulos, Ioannis N.; Ferdousi, Maryam; Ponirakis, Georgios; Asghar, Omar; Alam, Uazman; Kamran, Saadat; Mahfoud, Ziyad; Efron, Nathan; Malik, Rayaz A.; Qidwai, Uvais

doi:10.2337/dc20-2012

Cited by 28 publications

(19 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our AI-based DLA achieved comparable results in participants with diabetic neuropathy, but additionally differentiated healthy people from individuals with prediabetes or diabetes without neuropathy, indicating that our AI-based DLA detects early subclinical neuropathy in a real-world clinical setting. Recently, Salahouddin et al [ 46 ] developed a novel automated AI-based analysis system which rapidly quantified CNFL and classified patients with diabetic neuropathy using an adaptive neuro-fuzzy inference system, achieving an AUC of 0.95 (92% sensitivity/80% specificity) for discriminating patients with and without diabetic neuropathy. We propose the instigation of a screening programme for diabetic neuropathy utilising CCM alongside diabetic retinopathy screening [ 47 ].…”

Section: Discussionmentioning

confidence: 99%

“…Our study was based on a relatively small dataset ( N = 369 participants), resulting in wide CIs, but nevertheless achieved reasonable classification accuracy. Furthermore, only one image from each participant was used, unlike previous studies [ 18 , 21 , 22 , 46 ] which have used multiple images. Indeed, despite defining diabetic neuropathy using the Toronto criteria [ 27 ], which rely on abnormal nerve conduction [ 5 ], our AI-based DLA, which identifies small fibre pathology known to precede large fibre involvement, still achieved reasonable outcomes.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2021

Self Cite

View full text Add to dashboard Cite

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

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

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

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, machine learning algorithms showed excellent performance in medical image analysis. Several artificial intelligence-based methods have been developed to improve the less-than-ideal results by ACCM 29 , 30 . In two prior studies, NFL measured using machine learning techniques was comparable to that obtained using manual method and was significantly better than results by ACCM 29 , 30 .…”

Section: Discussionmentioning

confidence: 99%

“…Several artificial intelligence-based methods have been developed to improve the less-than-ideal results by ACCM 29 , 30 . In two prior studies, NFL measured using machine learning techniques was comparable to that obtained using manual method and was significantly better than results by ACCM 29 , 30 . Therefore, in addition to outsourcing this task to beginner observers, the utilization of artificial intelligence-based automated methods may be another option to reduce the labor- and time-associated cost of training professional image-readers.…”

Section: Discussionmentioning

confidence: 99%

Comparing the results of manual and automated quantitative corneal neuroanalysing modules for beginners

Hsieh

et al. 2021

Sci Rep

View full text Add to dashboard Cite

This study aimed to evaluate the reliability of in vivo confocal microscopic neuroanalysis by beginners using manual and automated modules. Images of sub-basal corneal nerve plexus (SCNP) from 108 images of 18 healthy participants were analyzed by 7 beginner observers using manual (CCMetrics, [CCM]) and automated (ACCMetrics, [ACCM]) module. SCNP parameters analyzed included corneal nerve fiber density (NFD), corneal nerve branch density (NBD), corneal nerve fiber length (NFL), and tortuosity coefficient (TC). The intra-observer repeatability, inter-observer reliability, inter-module agreement, and left–right eye symmetry level of SCNP parameters were examined. All observers showed good intra-observer repeatability using CCM (intraclass correlation coefficient [ICC] > 0.60 for all), except when measuring TC. Two observers demonstrated especially excellent repeatability in analyzing NFD, NBD, and NFL using manual mode, indicating the quality of interpretation may still be observer-dependent. Among all SCNP parameters, NFL had the best inter-observer reliability (Spearman’s rank-sum correlation coefficient [SpCC] and ICC > 0.85 for the 3 original observers) and left–right symmetry level (SpCC and ICC > 0.60). In the additional analysis of inter-observer reliability using results by all 7 observers, only NFL showed good inter-observer reliability (ICC = 0.79). Compared with CCM measurements, values of ACCM measurements were significantly lower, implying a poor inter-module agreement. Our result suggested that performance of quantitative corneal neuroanalysis by beginners maybe acceptable, with NFL being the most reliable parameter, and automated method cannot fully replace manual work.

show abstract

“…Corneal nerve fiber density (CNFD) (fibers/mm 2 ), branch density (CNBD) (branches/mm 2 ), and fiber length (CNFL) (total fiber length mm/mm 2 ) are most commonly quantified using manual and automated image analysis software [30,31] and a normative range has been established, taking into account age and gender in a large, healthy control cohort [32]. Recently, artificial intelligence (AI) -based deep learning algorithms have been applied to augment corneal nerve analysis and the classification of patients with and without diabetic neuropathy [33,34]. The imaging procedure is relatively simple and the technique can be learnt by investigators without an ophthalmic background with 2-3 days of intensive training.…”

Section: Corneal Confocal Microscopy: Discovery and Methodsmentioning

confidence: 99%

Corneal Confocal Microscopy in the Diagnosis of Small Fiber Neuropathy: Faster, Easier, and More Efficient Than Skin Biopsy?

et al. 2021

Self Cite

View full text Add to dashboard Cite

Chronic pain may affect 30–50% of the world’s population and an important cause is small fiber neuropathy (SFN). Recent research suggests that autoimmune diseases may be one of the most common causes of small nerve fiber damage. There is low awareness of SFN among patients and clinicians and it is difficult to diagnose as routine electrophysiological methods only detect large fiber abnormalities, and specialized small fiber tests, like skin biopsy and quantitative sensory testing, are not routinely available. Corneal confocal microscopy (CCM) is a rapid, non-invasive, reproducible method for quantifying small nerve fiber degeneration and regeneration, and could be an important tool for diagnosing SFN. This review considers the advantages and disadvantages of CCM and highlights the evolution of this technique from a research tool to a diagnostic test for small fiber damage, which can be a valuable contribution to the study and management of autoimmune disease.

show abstract

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

Cited by 28 publications

References 5 publications

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

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

Comparing the results of manual and automated quantitative corneal neuroanalysing modules for beginners

Corneal Confocal Microscopy in the Diagnosis of Small Fiber Neuropathy: Faster, Easier, and More Efficient Than Skin Biopsy?

Contact Info

Product

Resources

About