arXiv 2508.037382025-07-31eess.IVcs.AIcs.CV

改进视网膜动脉/静脉分类的通道耦合方法

Improve Retinal Artery/Vein Classification via Channel Couplin

Institute of Medical Technology, Peking University Health Science Center, Peking University, Beijing, China（北京大学医学部医学技术研究所）；Department of Biomedical Engineering, Peking University, Beijing, China（北京大学生物医学工程系）；National Biomedical Imaging Center, Peking University, Beijing, China（北京大学国家生物医学成像中心）；Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology（佐治亚理工学院生物医学工程系）；Emory University, Atlanta, GA, USA（埃默里大学）

Shuang Zeng, Chee Hong Lee, Kaiwen Li, Boxu Xie, Ourui Fu, Hangzhou He, Lei Zhu, Yanye Lu, Fangxiao Cheng

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对视网膜动脉/静脉分类中忽略血管结构耦合关系的问题，提出通道耦合血管一致性损失和图像内像素级对比损失，在RITE、LES-AV和HRF数据集上取得最先进结果。

摘要：

视网膜血管分割在分析眼底图像以诊断全身性和眼部疾病中起着至关重要的作用。在此基础上，将分割出的血管进一步分类为动脉和静脉（A/V），能够提取临床上相关的特征，如血管宽度、直径和弯曲度，这些特征对于检测糖尿病和高血压视网膜病变等疾病至关重要。然而，手动分割和分类耗时、成本高且不一致。随着卷积神经网络的发展，已经提出了多种自动化方法来解决这一挑战，但仍存在一些问题。例如，现有方法都将动脉、静脉和整体血管分割视为三个独立的二值任务，忽略了这些解剖结构之间的内在耦合关系。考虑到动脉和静脉结构是整体视网膜血管图的子集，并且自然应与其预测保持一致，我们设计了一种新颖的损失函数，名为通道耦合血管一致性损失（Channel-Coupled Vessel Consistency Loss），以强制血管、动脉和静脉预测之间的连贯性和一致性，避免网络偏向于三个简单的二值分割任务。此外，我们还引入了一个正则化项，名为图像内像素级对比损失（intra-image pixel-level contrastive loss），以提取更具判别性的特征级细粒度表示，用于准确的视网膜A/V分类。在包括RITE、LES-AV和HRF在内的三个公开A/V分类数据集上取得了最先进（SOTA）的结果。我们的代码将在论文被接收后公开。

英文摘要：

Retinal vessel segmentation plays a vital role in analyzing fundus images for the diagnosis of systemic and ocular diseases. Building on this, classifying segmented vessels into arteries and veins (A/V) further enables the extraction of clinically relevant features such as vessel width, diameter and tortuosity, which are essential for detecting conditions like diabetic and hypertensive retinopathy. However, manual segmentation and classification are time-consuming, costly and inconsistent. With the advancement of Convolutional Neural Networks, several automated methods have been proposed to address this challenge, but there are still some issues. For example, the existing methods all treat artery, vein and overall vessel segmentation as three separate binary tasks, neglecting the intrinsic coupling relationships between these anatomical structures. Considering artery and vein structures are subsets of the overall retinal vessel map and should naturally exhibit prediction consistency with it, we design a novel loss named Channel-Coupled Vessel Consistency Loss to enforce the coherence and consistency between vessel, artery and vein predictions, avoiding biasing the network toward three simple binary segmentation tasks. Moreover, we also introduce a regularization term named intra-image pixel-level contrastive loss to extract more discriminative feature-level fine-grained representations for accurate retinal A/V classification. SOTA results have been achieved across three public A/V classification datasets including RITE, LES-AV and HRF. Our code will be available upon acceptance.

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。