针对视网膜血管细末梢易漏检问题，提出多尺度融合网络提升分割精度。
HMS-VesselNet: Hierarchical Multi-Scale Attention Network with Topology-Preserving Loss for Retinal Vessel Segmentation
- 四分支并行处理多尺度图像，融合权重可学习
- 联合优化面积重叠与血管连续性，提升对细血管的召回率
- 在3个数据集上均显著改善细小周边血管分割效果
基于标准重叠损失的视网膜血管分割方法常遗漏细小的外周血管，因其像素占比极低且与背景对比度弱。本文提出HMS-VesselNet，一种分层多尺度网络，通过四个并行分支在不同分辨率下处理眼底图像，并利用可学习融合权重整合输出。训练损失结合Dice、二值交叉熵和中心线Dice，联合优化区域重叠与血管连续性。从第20轮开始采用困难样本挖掘，集中梯度更新于最难点图像。在DRIVE、STARE和CHASE_DB1共68张图像上进行5折交叉验证，平均Dice达88.72±0.67%，敏感性为90.78±1.42%，AUC为98.25±0.21%。在留一数据集外实验中，各未见数据集的AUC均高于95%。最大提升体现在细小外周血管的召回率，此类结构最易被传统方法忽略，却对糖尿病视网膜病变早期诊断至关重要。
原文摘要 · Abstract (English)
Retinal vessel segmentation methods based on standard overlap losses tend to miss thin peripheral vessels because these structures occupy very few pixels and have low contrast against the background. We propose HMS-VesselNet, a hierarchical multi-scale network that processes fundus images across four parallel branches at different resolutions and combines their outputs using learned fusion weights. The training loss combines Dice, binary cross-entropy, and centerline Dice to jointly optimize area overlap and vessel continuity. Hard example mining is applied from epoch 20 onward to concentrate gradient updates on the most difficult training images. Tested on 68 images from DRIVE, STARE, and CHASE_DB1 using 5-fold cross-validation, the model achieves a mean Dice of 88.72 +/- 0.67%, Sensitivity of 90.78 +/- 1.42%, and AUC of 98.25 +/- 0.21%. In leave-one-dataset-out experiments, AUC remains above 95% on each unseen dataset. The largest improvement is in the recall of thin peripheral vessels, which are the structures most frequently missed by standard methods and most critical for early detection of diabetic retinopathy.
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。