发表机构
Julius-Maximilians-Universität Würzburg; University Hospital Würzburg（维尔茨堡大学; 维尔茨堡大学医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对pCLE图像马赛克配准，构建含132对帧对的数据集，评估从平移到TPS的变换模型及六种匹配后端，发现TPS最佳，且需直接评估马赛克质量。
AI 中文摘要
共聚焦激光内窥显微镜（CLE）提供实时、细胞级分辨率的光学活检，但视野狭窄，图像马赛克技术可扩展视野以提供解剖背景。由于逐行采集、探头运动以及探头与组织之间的相互作用，帧对齐通常需要非线性变换，其精度难以量化：灵活的变换模型可能拟合强度特征和噪声，因此基于外观的度量（如归一化互相关（NCC））可能改善，但几何精度并无真正提升。为此，我们建立了一个包含来自4名患者的14个pCLE序列中的132对帧对的数据集，并手动标注了地标对应关系，使目标配准误差（TRE）可作为NCC的几何基础补充。我们评估了逐步增加变换模型自由度（从平移到薄板样条（TPS））以及六种特征匹配后端的效果，这些后端涵盖经典方法（Shi-Tomasi、Lucas-Kanade）和学习方法（SuperPoint、SuperGlue、LightGlue、LoFTR、RoMa）。在组织变形下，平移和刚性模型被证明不足，而采用随机采样的TPS在所评估配置中实现了最强的基于地标的对齐；在学习匹配器中，未经微调使用时，只有RoMa提供了稳健但适度的优势。在序列层面，成对配准质量被证明是最终马赛克质量的不可靠预测指标，因此必须直接评估马赛克质量，而非从成对指标推断。
英文摘要
Confocal Laser Endomicroscopy (CLE) provides real-time, cellular-resolution optical biopsy but has a narrow field of view, which image mosaicing can extend to provide anatomical context. Because of line-by-line acquisition, probe motion, and probe-tissue interaction, frame alignment generally requires a non-linear transformation whose accuracy is difficult to quantify: flexible transformation models can fit intensity features and noise, so appearance-based metrics such as Normalized Cross-Correlation (NCC) can improve without a genuine gain in geometric accuracy. We therefore establish a dataset of 132 frame pairs across fourteen pCLE sequences from 4 patients with manually annotated landmark correspondences, so that Target Registration Error (TRE) can serve as a geometrically grounded complement to NCC. We assess the effect of progressively increasing the transformation model's degrees of freedom, from translation to Thin Plate Spline (TPS), and of six feature-matching backends spanning classical (Shi-Tomasi, Lucas-Kanade) and learned (SuperPoint, SuperGlue, LightGlue, LoFTR, RoMa) approaches. Translation and rigid models prove insufficient under tissue deformation, while TPS with random sampling achieves the strongest landmark-derived alignment of the evaluated configurations; among the learned matchers, used without fine-tuning, only RoMa offers a robust, if modest, advantage over other methods. At the sequence level, pairwise registration quality proved an unreliable predictor of final mosaic quality, so mosaic quality must be evaluated directly rather than inferred from pairwise metrics.
