用深度学习集成模型预测糖尿病视网膜病变，提前一年预警高风险患者。
Deep Learning Ensemble for Predicting Diabetic Macular Edema Onset Using Ultra-Wide Field Color Fundus Image
- 融合ResNet、DenseNet等多模型，提升预测鲁棒性。
- 在合成数据集上达到AUC 0.7017，F1值0.6512。
- 适合临床早期筛查，辅助医生制定治疗方案。
糖尿病性黄斑水肿（DME）是糖尿病的严重并发症，表现为视网膜中央区域因积液而增厚，是导致糖尿病患者视力损伤的主要原因之一。中心受累型DME（ci-DME）风险最高，因液体接近负责清晰中央视觉的黄斑区。早期预测ci-DME可改善治疗效果。本文提出一种集成方法，基于DIAMOND挑战赛提供的合成超广角彩色眼底图像（UWF-CFP），使用ResNet、DenseNet、EfficientNet和VGG等先进分类网络构建模型。表现最佳的DenseNet-121、ResNet-152和EfficientNet-b7被集成至最终预测模型。在合成测试集上，该模型取得AUC 0.7017、F1分数0.6512及预期校准误差（ECE）0.2057的性能。结果优于或媲美以往在高度优化数据集上使用传统眼底摄影或超广角摄影的记录。此前研究中人类或计算机诊断的最优敏感度为67.3%–98%，特异性为47.8%–80%。因此，本方法可在多种场景安全有效应用，有助于ci-DME的早期发现、更优治疗决策与预后评估。
原文摘要 · Abstract (English)
Diabetic macular edema (DME) is a severe complication of diabetes, characterized by thickening of the central portion of the retina due to accumulation of fluid. DME is a significant and common cause of visual impairment in diabetic patients. Center-involved DME (ci-DME) is the highest risk form of disease because fluid extends close to the fovea which is responsible for sharp central vision. Earlier diagnosis or prediction of ci-DME may improve treatment outcomes. Here, we propose an ensemble method to predict ci-DME onset within a year, after using synthetic ultra-wide field color fundus photography (UWF-CFP) images provided by the DIAMOND Challenge during development. We adopted a variety of baseline state-of-the-art classification networks including ResNet, DenseNet, EfficientNet, and VGG with the aim of enhancing model robustness. The best performing models were Densenet-121, Resnet-152 and EfficientNet-b7, and these were assembled into a definitive predictive model. The final ensemble model demonstrates a strong performance with an Area Under Curve (AUC) of 0.7017, an F1 score of 0.6512, and an Expected Calibration Error (ECE) of 0.2057 when deployed on the synthetic test dataset. Results from our ensemble model were superior/comparable to previous recorded results in highly curated settings using conventional fundus photography/ultra-wide field fundus photography. Optimal sensitivity in previous studies (using humans or computers to diagnose) ranges from 67.3%-98%, specificity from 47.8%-80%. Therefore, our method can be used safely and effectively in a range of settings may facilitate earlier diagnosis, better treatment decisions, and improved prognostication in ci-DME.
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。