ARCOS：面向跨光学相干断层扫描设备的角膜层分割的零样本边界定位方法
ARCOS: Zero-shot Boundary Localization for Corneal Layer Segmentation Across Optical Coherence Tomography Devices
浏览论文内容
中文总结 AI 辅助
本研究提出ARCOS零样本边界定位框架，用于跨设备OCT图像的角膜层分割，在匹配设备测试集及零样本跨设备评估中均优于基线模型，实现了高精度的边界定位与厚度估计。
中文摘要 AI 辅助
光学相干断层扫描（OCT）中角膜层的精确分割对于角膜形态的定量评估至关重要，包括层厚度以及与疾病或手术相关的结构变化。然而，自动分割仍然具有挑战性，因为角膜界面很薄，受散斑噪声影响，并且在不同采集设备之间存在差异。在这项工作中，我们提出了ARCOS，一种用于临床前段OCT图像中角膜层分割的基于patch的零样本边界定位框架。该方法不执行传统的区域分类，而是从重叠的原生分辨率patch中预测主要角膜界面的边界热图。将patch级别的预测拼接成完整的B-scan，并转换为边界位置，以获得连续的、按解剖学顺序排列的层分割结果。该网络将多尺度特征融合与自条件细化模块相结合，该模块利用中间边界信息来改进局部热图预测，同时保留空间细节。该方法在从多个设备采集的临床OCT图像上进行了评估，并与代表性的分割基线方法进行了边界定位和衍生厚度指标的比较。所提出的方法在匹配设备测试集上实现了95.1%的差一个边界定位准确率和0.514像素的平均绝对边界误差。在零样本跨设备评估中，它在未见过的采集设备上保持了84.3%的平均差一个准确率和0.855像素的平均绝对边界误差，优于基线模型。从预测边界得出的厚度估计值在整个角膜区域显示出较低的误差，支持该方法用于定量角膜OCT分析。
英文摘要
Accurate segmentation of corneal layers in optical coherence tomography (OCT) is essential for quantitative assessment of corneal morphology, including layer thickness and structural changes associated with disease or surgery. However, automatic segmentation remains challenging because corneal interfaces are thin, affected by speckle noise, and variable across acquisition devices. In this work, we propose ARCOS, a patch-based zero-shot boundary localization framework for corneal layer segmentation in clinical anterior-segment OCT images. Rather than performing conventional region classification, the method predicts boundary heatmaps for the main corneal interfaces from overlapping native-resolution patches. Patch-level predictions are stitched across the full B-scan and converted into boundary locations to obtain continuous, anatomically ordered layer segmentations. The network combines multi-scale feature fusion with a self-conditioned refinement module that uses intermediate boundary information to improve local heatmap predictions while preserving spatial detail. The method was evaluated on clinical OCT images acquired from multiple devices and compared with representative segmentation baselines using boundary localization and derived thickness metrics. The proposed method achieved an off-by-one boundary localization accuracy of 95.1% and a mean absolute boundary error of 0.514 pixels on the matched-device test set. In zero-shot cross-device evaluation, it maintained an average off-by-one accuracy of 84.3% and a mean absolute boundary error of 0.855 pixels across unseen acquisition devices, outperforming the baseline models. Thickness estimates derived from the predicted boundaries showed low error across corneal regions, supporting the method's use for quantitative corneal OCT analysis.
发表机构
- Laboratoire d’Optique et Biosciences, CNRS, INSERM, École polytechnique, Institut Polytechnique de Paris（光学与生物光学实验室，法国国家科学研究中心，法国健康与医学研究院，巴黎综合理工学院，巴黎理工学院）
- GRC 32, Transplantation et Thérapies Innovantes de la Cornée, Sorbonne Université, Centre Hospitalier National d’Ophtalmologie des Quinze-Vingts（GRC 32，角膜创新移植与治疗研究组，索邦大学，十五二十国家眼科中心）
机构由 AI 辅助整理，请以论文原文为准。
