发表机构
The University of Akron（阿克伦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述梳理视盘分割技术从经典方法到现代AI方法的发展，总结核心原则，指出边界模糊等持续挑战，为该领域研究提供方法学参考。
AI 中文摘要
准确的视盘（Optic Disc，OD）定位与分割对视网膜图像分析及青光眼评估至关重要，但因光照变化、病理干扰、血管遮挡及边界定义模糊等问题，该任务仍具挑战性。本结构化方法学综述梳理了视盘分割技术从经典图像处理、可变形模型到当代基于人工智能（AI）方法的发展历程，通过结构化文献检索与研究筛选流程，确定了涵盖主要方法学进展的代表性研究。综述首先总结了常用的眼底图像数据集，随后按主要机制分类梳理经典方法，包括强度与阈值法、直方图与熵分析、形态学、几何与霍夫变换（Hough-transform）方法、滤波与特征算子、基于纹理与区域的方法，以及主动轮廓与水平集模型。本文特别关注这些方法在视盘定位与边界描绘中的假设、优势、局限性及互补作用。随后对代表性AI方法进行考察，以展示从手工特征与显式定义先验到学习表征、基于Transformer的分割、边界与形状感知学习、可提示分割及视网膜基础模型的转变。在这些方法学代际中，若干核心分割原则始终存在，包括感兴趣区域定位、多尺度表征、几何与解剖学约束及边界正则化，尽管其实现方式已从预定义算子转变为学习模块、损失函数、提示及预训练表征。综述进一步指出，边界模糊、解剖学变异、域偏移及跨数据集泛化仍是持续存在的挑战。
英文摘要
Accurate localization and segmentation of the optic disc (OD) are important for retinal image analysis and glaucoma assessment, yet remain challenging due to variations in illumination, pathology, vascular interference, and poorly defined boundaries. This structured methodological review examines the evolution of OD segmentation from classical image-processing and deformable models to contemporary artificial intelligence (AI)-based approaches. A structured literature search and study-selection process was used to identify representative studies spanning major methodological developments. The review first summarizes commonly used fundus-image datasets, then organizes classical methods by principal mechanisms, including intensity and thresholding, histogram and entropy analysis, morphology, geometric and Hough-transform methods, filtering and feature operators, texture- and region-based approaches, and active-contour and level-set models. This paper pays particular attention to the assumptions, strengths, limitations, and complementary roles of these methods in OD localization and boundary delineation. Representative AI approaches are subsequently examined to illustrate the transition from handcrafted features and explicitly defined priors to learned representations, Transformer-based segmentation, boundary- and shape-aware learning, promptable segmentation, and retinal foundation models. Across these methodological generations, several core segmentation principles persist, including region-of-interest localization, multiscale representation, geometric and anatomical constraints, and boundary regularization, although their implementation has shifted from predefined operators to learned modules, losses, prompts, and pretrained representations. The review further identifies boundary ambiguity, anatomical variability, domain shift, and cross-dataset generalization as continuing challenges.
