通过多角度眼白血管图像，用深度学习无创估算血糖水平。
Deep Learning Based Estimation of Blood Glucose Levels from Multidirectional Scleral Blood Vessel Imaging
- 构建多视角深度网络，融合不同注视方向的血管特征。
- 血糖预测误差仅6.42 mg/dL，与实验室结果高度相关。
- 适合糖尿病患者日常监测，无需采血，可推广至家庭场景。
定期监测血糖对糖尿病管理至关重要，但传统血液检测频繁使用不便。巩膜表层微血管可能呈现糖尿病相关变化，且在眼球表面可见。本文提出ScleraGluNet，一种基于多视角深度学习的框架，用于三类代谢状态分类（正常、控制型糖尿病、高血糖糖尿病）及连续空腹血浆葡萄糖（FPG）估计。数据集包含445名参与者（150/140/155人），每人五种注视方向采集2,225张前段图像。经血管增强后，采用并行卷积分支提取特征，通过矛鱼觅食优化（MRFO）精炼，并以基于Transformer的跨视角注意力融合。采用受试者级五折交叉验证，每名参与者所有图像归入同一折。ScleraGluNet总体准确率达93.8%，正常、控制型糖尿病、高血糖糖尿病的一对多AUC分别为0.971、0.956、0.982。在FPG估计中，平均绝对误差（MAE）为6.42 mg/dL，均方根误差（RMSE）为7.91 mg/dL，与实验室测量相关系数r=0.983，决定系数R²=0.966。Bland-Altman分析显示均值偏差为+1.45 mg/dL，95%一致性界限为-8.33至+11.23 mg/dL。结果表明，多角度巩膜血管成像结合多视图学习是一种有前景的无创血糖评估方法，需多中心验证后方可临床应用。
原文摘要 · Abstract (English)
Regular monitoring of glycemic status is essential for diabetes management, yet conventional blood-based testing can be burdensome for frequent assessment. The sclera contains superficial microvasculature that may exhibit diabetes related alterations and is readily visible on the ocular surface. We propose ScleraGluNet, a multiview deep-learning framework for three-class metabolic status classification (normal, controlled diabetes, and high-glucose diabetes) and continuous fasting plasma glucose (FPG) estimation from multidirectional scleral vessel images. The dataset comprised 445 participants (150/140/155) and 2,225 anterior-segment images acquired from five gaze directions per participant. After vascular enhancement, features were extracted using parallel convolutional branches, refined with Manta Ray Foraging Optimization (MRFO), and fused via transformer-based cross-view attention. Performance was evaluated using subject-wise five-fold cross-validation, with all images from each participant assigned to the same fold. ScleraGluNet achieved 93.8% overall accuracy, with one-vs-rest AUCs of 0.971,0.956, and 0.982 for normal, controlled diabetes, and high-glucose diabetes, respectively. For FPG estimation, the model achieved MAE = 6.42 mg/dL and RMSE = 7.91 mg/dL, with strong correlation to laboratory measurements (r = 0.983; R2 = 0.966). Bland Altman analysis showed a mean bias of +1.45 mg/dL with 95% limits of agreement from -8.33 to +11.23$ mg/dL. These results support multidirectional scleral vessel imaging with multiview learning as a promising noninvasive approach for glycemic assessment, warranting multicenter validation before clinical deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。