ConKeD++ —— 改进视网膜图像配准的描述符学习：对比损失的全面研究
ConKeD++ -- Improving descriptor learning for retinal image registration: A comprehensive study of contrastive losses
AI总结：
本研究扩展并改进了彩色眼底图像配准框架ConKeD，通过适配多种对比损失函数，并在FIRE等基准及新数据集上取得SOTA性能。
摘要：
自监督对比学习已成为最成功的深度学习范式之一。在此方面，它已广泛应用于图像配准，近期更涉足医学图像配准这一特定领域。在本研究中，我们提出测试、扩展并改进用于彩色眼底图像配准的最先进框架ConKeD。利用ConKeD框架，我们测试了多种损失函数，并将其适配于该框架与应用领域。此外，我们使用标准化基准数据集FIRE以及多个此前从未用于彩色眼底配准的数据集来评估模型，同时发布了这些数据集的配对数据及标准化评估方法。我们的研究在所有数据集和指标上均展现出最先进的性能，证明了其相较于当前SOTA彩色眼底配准方法的诸多优势。
英文摘要：
Self-supervised contrastive learning has emerged as one of the most successful deep learning paradigms. In this regard, it has seen extensive use in image registration and, more recently, in the particular field of medical image registration. In this work, we propose to test and extend and improve a state-of-the-art framework for color fundus image registration, ConKeD. Using the ConKeD framework we test multiple loss functions, adapting them to the framework and the application domain. Furthermore, we evaluate our models using the standarized benchmark dataset FIRE as well as several datasets that have never been used before for color fundus registration, for which we are releasing the pairing data as well as a standardized evaluation approach. Our work demonstrates state-of-the-art performance across all datasets and metrics demonstrating several advantages over current SOTA color fundus registration methods
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。
