Artificial Intelligence Analysis of Nerve Fibers Based on Corneal Confocal Microscopy

Abstract

Diabetic peripheral neuropathy (DPN) is one of the most common chronic complications of diabetes. Traditional DPN diagnostic methods are based on clinical symptoms and signs as well as electrophysiological examination, which are mainly used to detect the lesions of large nerve fibers. However, the small nerve fibers are the earliest ones damaged in DPN. Corneal confocal microscopy (CCM) can analyze the changes of corneal nerve fibers under a high power microscope. It is a rapid, repeatable and quantitative noninvasive technique to measure small nerve fibers. It can diagnose DPN early and evaluate neuromorphological changes prospectively. It has a good application expectation. During this article, we summarized the role and limitations of DPN's most reliable parameters of corneal nerve in evaluating diabetic autonomic neuropathy and diabetic micro-vascular complications. Further, we reviewed the clinical application of CCM in evaluating diabetic neuropathy and analysis methods of CCM related artificial intelligence, in order to provide references for clinical diagnosis and treatment.

Keywords

• artificial intelligence
• deep learning
• corneal confocal microscopy
• diabetic peripheral neuropathy