人工智能利用角膜共聚焦显微镜诊断糖尿病和糖尿病前期的周围神经病变,Diabetologia

当前位置： X-MOL 学术 › Diabetol. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

人工智能利用角膜共聚焦显微镜诊断糖尿病和糖尿病前期的周围神经病变
Diabetologia ( IF 8.4 ) Pub Date : 2021-11-21 , DOI: 10.1007/s00125-021-05617-x
Frank G Preston ₁ , Yanda Meng ₁ , Jamie Burgess ₂ , Maryam Ferdousi ₃ , Shazli Azmi ₃ , Ioannis N Petropoulos ₄ , Stephen Kaye ₁ , Rayaz A Malik ₄ , Yalin Zheng _{1,

5} , Uazman Alam _{2,

6}

Affiliation

目标/假设

我们旨在开发一种基于人工智能 (AI) 的深度学习算法 (DLA)，将无需图像分割的归因方法应用于角膜共聚焦显微镜图像，并准确分类周围神经病变（或缺乏）。

方法

基于 AI 的 DLA 利用具有数据增强功能的卷积神经网络来提高算法的通用性。该算法使用高端图形处理器对 329 个角膜神经图像进行了 300 个时期的训练，并在 40 个图像（1 个图像/参与者）上进行了测试。参与者包括健康志愿者 (HV) 参与者 ( n = 90) 和 1 型糖尿病 ( n = 88)、2 型糖尿病 ( n = 141) 和前驱糖尿病 ( n = 50) 参与者（定义为空腹血糖受损、葡萄糖受损耐受性或两者的组合），并分为 HV、无神经病变 (PN-) ( n = 149) 和有神经病变 (PN+) ( n = 130)。对于基于 AI 的 DLA，开发了一种名为 ResNet-50 的改进残差神经网络，用于从图像中提取特征并执行分类。该算法在 40 名参与者（15 HV、13 PN-、12 PN+）上进行了测试。归因方法梯度加权类激活映射 (Grad-CAM)、Guided Grad-CAM 和遮挡敏感度显示了图像中对算法决策影响最大的区域。

结果

结果如下： HV：召回率为 1.0（95% CI 1.0, 1.0），精度为 0.83（95% CI 0.65, 1.0），F ₁ -score 为 0.91（95% CI 0.79, 1.0）；PN-：召回率为 0.85 (95% CI 0.62, 1.0)，精度为 0.92 (95% CI 0.73, 1.0)，F ₁ - 分数为 0.88 (95% CI 0.71, 1.0)；PN+：召回率为 0.83 (95% CI 0.58, 1.0)，精度为 1.0 (95% CI 1.0, 1.0)，F ₁分数为 0.91 (95% CI 0.74, 1.0)。归因方法显示的特征表明 HV 中有更多的角膜神经，PN- 的角膜神经减少，而 PN+ 图像的角膜神经缺失。

结论/解释

我们展示了使用单个角膜图像对周围神经病变进行快速分类的有希望的结果。需要一项大规模的多中心验证研究来评估基于 AI 的 DLA 在糖尿病神经病变筛查和诊断项目中的效用。

图形概要

"点击查看英文标题和摘要"

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

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

更新日期：2021-11-21

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南