医学级糖尿病视网膜病变分级系统，兼顾准确率与不确定性判断。
Multi-Channel Feature Fusion and Monte Carlo Dropout for Uncertainty-Aware Diabetic Retinopathy Grading
- 用绿色通道CLAHE增强特征，提升病变区域可见性。
- 在APTOS-2019数据集上达QWK 91.31%，20%转诊率下仍保持90.40%一致性。
- 通过蒙特卡洛丢弃和Grad-CAM实现可解释性，适合临床部署。
自动化五阶段糖尿病视网膜病变（DR）分级不仅需要高精度，还要求具备病灶感知预处理、序数预测、校准的不确定性估计和可解释性，以支持可靠的医疗诊断系统。本文提出一个统一流程：采用Ben-Graham绿色通道CLAHE特征表示、EfficientNetV2-L序数回归器，结合蒙特卡洛丢弃实现不确定性驱动转诊，同时利用Grad-CAM提供与临床相关病灶对齐的视觉解释。该方法在APTOS-2019官方测试集上达到91.31%的加权κ值，处于近乎完美一致区间（>80%）。在20%转诊率下，366张图像中有293张可自动分级，此时加权κ值为90.40%。更复杂的病例被转诊至专科评估，展示了分级质量、自动化程度与患者安全之间的实用权衡，构建了稳健、可靠且可部署的医疗诊断系统。
原文摘要 · Abstract (English)
Automated five-stage diabetic retinopathy (DR) grading requires more than high accuracy alone. Medical-grade deployment calls for lesion-aware preprocessing, ordinal predictions, calibrated uncertainty, and explainability to support reliable diagnostic systems. We present a unified pipeline that addresses these requirements using a Ben-Graham-green-channel CLAHE feature representation, an EfficientNetV2-L ordinal regressor, and Monte Carlo dropout for uncertainty-driven referral. Grad-CAM provides visual explanations aligned with clinically relevant lesions. The proposed method achieves a QWK of 91.31% on the APTOS-2019 official test split, placing it within the near-perfect agreement band (>80%). At a 20% referral rate, 293 of 366 images are automatically graded with a QWK of 90.40%. More complex cases are referred for specialist assessment, demonstrating a practical trade-off among grading quality, automation, and patient safety in robust, reliable, and deployment-ready medical diagnostic systems.
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。