轻量级模型实现糖尿病视网膜病变自动分级，适合移动端快速筛查。
Mobile-Ready Automated Triage of Diabetic Retinopathy Using Digital Fundus Images
- 基于MobileNetV3与有序标签头，兼顾精度与计算效率。
- 在APTOS 2019和IDRiD数据集上达QWK 0.9019，准确率80.03%。
- 针对移动设备优化，可部署于资源受限的基层医疗场景。
糖尿病视网膜病变（DR）是全球视力损伤的主要原因。然而，人工诊断耗时且易出错，导致筛查延迟。本文提出一种轻量级自动化深度学习框架，用于从数字眼底图像高效评估DR严重程度。采用MobileNetV3架构并结合一致排名逻辑（CORAL）头部，建模疾病有序进展的同时保持计算效率，适用于资源受限环境。模型在整合APTOS 2019与IDRiD数据集上训练验证，经圆形裁剪与光照归一化预处理。通过三折交叉验证与消融实验，结果表明：模型在测试集上取得0.9019的加权κ值（QWK）与80.03%的准确率。此外，通过模型校准缓解过自信问题，并针对移动端进行优化。该系统为早期糖尿病视网膜病变筛查提供了可扩展、实用的解决方案。
原文摘要 · Abstract (English)
Diabetic Retinopathy (DR) is a major cause of vision impairment worldwide. However, manual diagnosis is often time-consuming and prone to errors, leading to delays in screening. This paper presents a lightweight automated deep learning framework for efficient assessment of DR severity from digital fundus images. We use a MobileNetV3 architecture with a Consistent Rank Logits (CORAL) head to model the ordered progression of disease while maintaining computational efficiency for resource-constrained environments. The model is trained and validated on a combined dataset of APTOS 2019 and IDRiD images using a preprocessing pipeline including circular cropping and illumination normalization. Extensive experiments including 3-fold cross-validation and ablation studies demonstrate strong performance. The model achieves a Quadratic Weighted Kappa (QWK) score of 0.9019 and an accuracy of 80.03 percent. Additionally, we address real-world deployment challenges through model calibration to reduce overconfidence and optimization for mobile devices. The proposed system provides a scalable and practical tool for early-stage diabetic retinopathy screening.
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。