Qiao Qincheng, Xue Wen, Li Jinzhe, Zheng Wenwen, Yuan Yongkai, Li Chen, Liu Fuqiang, Hou Xinguo
Department of Endocrinology and Metabolism, Qilu Hospital, Shandong University, Jinan, China.
The First Clinical Medical College, Cheeloo College of Medicine, Shandong University, Jinan, China.
Digit Health. 2025 Mar 17;11:20552076251326223. doi: 10.1177/20552076251326223. eCollection 2025 Jan-Dec.
Diabetic peripheral neuropathy (DPN) is a common complication of diabetes, posing a significant risk for foot ulcers and amputation. Corneal confocal microscopy (CCM) is a rapid, noninvasive method to assess DPN by analysing corneal nerve fibre morphology. However, selecting high-quality representative images remains a critical challenge.
In this study, we propose a fully automated CCM image-selection algorithm based on deep learning feature extraction using ResNet-18 and unsupervised clustering. The algorithm consistently identifies representative images by balancing non-redundancy and representativeness, ensuring objectivity and reproducibility.
When validated against manual selection by researchers with varying expertise levels, the algorithm demonstrated superior performance in distinguishing DPN and reduced inter-observer variability. It completed the analysis of hundreds of images within 1 s, significantly enhancing diagnostic efficiency. Compared with traditional manual selection, the proposed method achieved higher diagnostic accuracy for key morphological parameters, including corneal nerve fibre density, length, and branch density.
The algorithm is open source and compatible with standard CCM workflows, offering researchers and clinicians a robust and efficient tool for DPN diagnosis. Further, multicentre studies are needed to validate these findings in diverse populations.
糖尿病周围神经病变（DPN）是糖尿病常见的并发症，会引发足部溃疡和截肢的重大风险。角膜共焦显微镜检查（CCM）是一种通过分析角膜神经纤维形态来评估DPN的快速、非侵入性方法。然而，选择高质量的代表性图像仍然是一个关键挑战。
在本研究中，我们提出了一种基于深度学习特征提取（使用ResNet - 18）和无监督聚类的全自动CCM图像选择算法。该算法通过平衡非冗余性和代表性来持续识别代表性图像，确保客观性和可重复性。
在与不同专业水平的研究人员进行手动选择验证时，该算法在区分DPN方面表现出卓越性能，并减少了观察者间的变异性。它在1秒内完成了数百张图像的分析，显著提高了诊断效率。与传统手动选择相比，该方法在关键形态学参数（包括角膜神经纤维密度、长度和分支密度）方面实现了更高的诊断准确性。
该算法是开源的，并且与标准CCM工作流程兼容，为研究人员和临床医生提供了一个用于DPN诊断的强大且高效的工具。此外，需要进行多中心研究以在不同人群中验证这些发现。
