Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model



Meng, Yanda ORCID: 0000-0001-7344-2174, Preston, Frank George ORCID: 0000-0002-3953-331X, Ferdousi, Maryam, Azmi, Shazli, Petropoulos, Ioannis Nikolaos, Kaye, Stephen ORCID: 0000-0003-0390-0592, Malik, Rayaz Ahmed, Alam, Uazman ORCID: 0000-0002-3190-1122 and Zheng, Yalin ORCID: 0000-0002-7873-0922
(2023) Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model. JOURNAL OF CLINICAL MEDICINE, 12 (4). 1284-.

[thumbnail of JCM_Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model.pdf] Text
JCM_Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model.pdf - Published version

Download (993kB) | Preview

Abstract

Diabetic peripheral neuropathy (DPN) is the leading cause of neuropathy worldwide resulting in excess morbidity and mortality. We aimed to develop an artificial intelligence deep learning algorithm to classify the presence or absence of peripheral neuropathy (PN) in participants with diabetes or pre-diabetes using corneal confocal microscopy (CCM) images of the sub-basal nerve plexus. A modified ResNet-50 model was trained to perform the binary classification of PN (PN+) versus no PN (PN-) based on the Toronto consensus criteria. A dataset of 279 participants (149 PN-, 130 PN+) was used to train (<i>n</i> = 200), validate (<i>n</i> = 18), and test (<i>n</i> = 61) the algorithm, utilizing one image per participant. The dataset consisted of participants with type 1 diabetes (<i>n</i> = 88), type 2 diabetes (<i>n</i> = 141), and pre-diabetes (<i>n</i> = 50). The algorithm was evaluated using diagnostic performance metrics and attribution-based methods (gradient-weighted class activation mapping (Grad-CAM) and Guided Grad-CAM). In detecting PN+, the AI-based DLA achieved a sensitivity of 0.91 (95%CI: 0.79-1.0), a specificity of 0.93 (95%CI: 0.83-1.0), and an area under the curve (AUC) of 0.95 (95%CI: 0.83-0.99). Our deep learning algorithm demonstrates excellent results for the diagnosis of PN using CCM. A large-scale prospective real-world study is required to validate its diagnostic efficacy prior to implementation in screening and diagnostic programmes.

Item Type: Article
Uncontrolled Keywords: artificial intelligence, corneal confocal microscopy, diabetic peripheral neuropathy
Divisions: Faculty of Health and Life Sciences
Faculty of Health and Life Sciences > Institute of Life Courses and Medical Sciences
Faculty of Health and Life Sciences > Institute of Life Courses and Medical Sciences > School of Medicine
Depositing User: Symplectic Admin
Date Deposited: 31 Mar 2023 10:01
Last Modified: 31 Mar 2023 10:02
DOI: 10.3390/jcm12041284
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3169381