基于特征初始配准与基于强度的实例优化的SHG与H&E图像自动配准：对COMULIS挑战赛的贡献
Automatic Registration of SHG and H&E Images with Feature-based Initial Alignment and Intensity-based Instance Optimization: Contribution to the COMULIS Challenge
AI总结：
本文提出一种无需训练的SHG与H&E图像自动配准方法，通过自动关键点匹配和基于实例优化的可变形配准解决多模态缺失数据问题，在外部验证集上达到88%初始配准成功率和2.48平均目标配准误差。
摘要：
将无创二次谐波显微成像自动配准到苏木精-伊红（H&E）切片是一个备受期待但尚未解决的问题。该任务具有挑战性，因为二次谐波图像仅包含部分信息，而染色的H&E切片提供了更多关于组织形态的信息。此外，两种成像方法具有不同的强度分布。因此，该任务可以被表述为带有缺失数据的多模态配准问题。在本研究中，我们提出了一种基于自动关键点匹配，随后进行基于实例优化的可变形配准的方法。该方法不需要任何训练，并使用COMULIS组织在Learn2Reg挑战赛中提供的数据集进行评估。该方法取得了相对较好的泛化能力，在外部验证集上的初始配准成功率达到88%，平均目标配准误差为2.48。我们公开了源代码，并将其整合到DeeperHistReg图像配准框架中。
英文摘要：
The automatic registration of noninvasive second-harmonic generation microscopy to hematoxylin and eosin slides is a highly desired, yet still unsolved problem. The task is challenging because the second-harmonic images contain only partial information, in contrast to the stained H&E slides that provide more information about the tissue morphology. Moreover, both imaging methods have different intensity distributions. Therefore, the task can be formulated as a multi-modal registration problem with missing data. In this work, we propose a method based on automatic keypoint matching followed by deformable registration based on instance optimization. The method does not require any training and is evaluated using the dataset provided in the Learn2Reg challenge by the COMULIS organization. The method achieved relatively good generalizability resulting in 88% of success rate in the initial alignment and average target registration error equal to 2.48 on the external validation set. We openly release the source code and incorporate it in the DeeperHistReg image registration framework.
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。
