通过前段眼影像实现糖尿病筛查的自动化:一种深度学习与可解释AI方法
Automated Diabetic Screening via Anterior Segment Ocular Imaging: A Deep Learning and Explainable AI Approach
AI总结:
本文提出利用前段眼影像进行糖尿病自动分类的深度学习方法,通过改进预处理和自监督学习提升模型性能,实现高精度的糖尿病状态分类。
摘要:
传统糖尿病视网膜病变筛查依赖视网膜摄影,需要专门设备和专业知识,常在初级保健和资源有限的环境中难以获得。我们开发并验证了一种深度学习系统,利用前段眼影像进行自动化糖尿病分类,这是一种使用标准摄影设备的可行替代方法。系统利用虹膜、脉络膜和结膜中的可见生物标记物,这些标记物与全身糖尿病状态相关。我们系统评估了五个当代架构(EfficientNet-V2-S结合自监督学习、Vision Transformer、Swin Transformer、ConvNeXt-Base和ResNet-50)在2640张临床标注的前段眼影像上的表现,涵盖正常、控制良好和未控制糖尿病类别。实施了结合镜面反射抑制和受限自适应直方图均衡化(CLAHE)的定制预处理流程,以增强对分类至关重要的细微血管和纹理模式。使用SimCLR进行自监督学习在特定眼科图像上显著提高了模型性能。EfficientNet-V2-S结合自监督学习实现了最优性能,F1得分为98.21%,精确度为97.90%,召回率为98.55%,显著优于仅使用ImageNet初始化(F1得分为94.63%)。值得注意的是,模型在正常分类上的精确度接近完美(100%),这对于减少不必要的临床转诊至关重要。
英文摘要:
Diabetic retinopathy screening traditionally relies on fundus photography, requiring specialized equipment and expertise often unavailable in primary care and resource limited settings. We developed and validated a deep learning (DL) system for automated diabetic classification using anterior segment ocular imaging a readily accessible alternative utilizing standard photography equipment. The system leverages visible biomarkers in the iris, sclera, and conjunctiva that correlate with systemic diabetic status. We systematically evaluated five contemporary architectures (EfficientNet-V2-S with self-supervised learning (SSL), Vision Transformer, Swin Transformer, ConvNeXt-Base, and ResNet-50) on 2,640 clinically annotated anterior segment images spanning Normal, Controlled Diabetic, and Uncontrolled Diabetic categories. A tailored preprocessing pipeline combining specular reflection mitigation and contrast limited adaptive histogram equalization (CLAHE) was implemented to enhance subtle vascular and textural patterns critical for classification. SSL using SimCLR on domain specific ocular images substantially improved model performance.EfficientNet-V2-S with SSL achieved optimal performance with an F1-score of 98.21%, precision of 97.90%, and recall of 98.55% a substantial improvement over ImageNet only initialization (94.63% F1). Notably, the model attained near perfect precision (100%) for Normal classification, critical for minimizing unnecessary clinical referrals.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。