Corneal confocal microscopy is a non-invasive technique used to identify peripheral and central neurodegenerative disease, but quantifying corneal sub-basal nerve plexus morphology is a lengthy process. In a new paper, researchers sought to create an artificial intelligence (AI)-based deep learning algorithm to quantify nerve fiber properties pertaining to the diagnosis of diabetic neuropathy; this development was compared to ACCMetrics, a validated automated analysis program. The deep learning algorithm developed by the study authors employed a convolutional neural network with data augmentation to automate the quantification of the corneal sub-basal nerve plexus to diagnose diabetic neuropathy. A high-end graphics processor unit of 1,698 corneal confocal microscopy images trained the algorithm, which was validated externally on 2,137 images. The goal of the algorithm was to identify total nerve fiber length, branch points, tail points, number and length of nerve segments, and fractal numbers. The newly developed algorithm presented superior intraclass correlation coefficients compared to those of ACCMetrics for total corneal nerve fiber 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). When classifying 90 patients with and 132 patients without neuropathy, the new algorithm achieved an area under the receiver operating characteristic curve of 0.83, specificity of 0.87, and sensitivity of 0.68.