NCF：用于医学图像配准的神经对应场
NCF: Neural Correspondence Field for Medical Image Registration
AI总结：
针对医学图像配准中数据稀缺和复杂形变问题，提出无需训练数据的神经对应场（NCF）方法，通过紧凑网络对单一图像对建模并优化专属参数，以极低参数量实现了优异的配准性能。
摘要：
可变形图像配准是医学图像处理中的一项基本任务。传统的基于优化的方法在处理复杂形变时往往难以保证准确性。近年来，基于学习的方法在公开数据集上取得了良好的性能，但医学图像数据的稀缺性使得构建一个能够处理多样化真实场景的泛化模型极具挑战。为了解决这一问题，我们提出了一种无需训练数据的基于学习的方法，即神经对应场（NCF），该方法仅需从一对数据中即可学习。我们的方法采用一个紧凑的神经网络来建模对应场，并针对每一对独立的图像对优化模型参数。因此，每对图像都拥有一组独特的网络权重。值得注意的是，我们的模型非常高效，仅使用0.06百万个参数。评估结果表明，所提方法在公开的Lung CT数据集上取得了优越的性能，并在头颈部数据集上优于传统方法，证明了其有效性与高效性。
英文摘要：
Deformable image registration is a fundamental task in medical image processing. Traditional optimization-based methods often struggle with accuracy in dealing with complex deformation. Recently, learning-based methods have achieved good performance on public datasets, but the scarcity of medical image data makes it challenging to build a generalizable model to handle diverse real-world scenarios. To address this, we propose a training-data-free learning-based method, Neural Correspondence Field (NCF), which can learn from just one data pair. Our approach employs a compact neural network to model the correspondence field and optimize model parameters for each individual image pair. Consequently, each pair has a unique set of network weights. Notably, our model is highly efficient, utilizing only 0.06 million parameters. Evaluation results showed that the proposed method achieved superior performance on a public Lung CT dataset and outperformed a traditional method on a head and neck dataset, demonstrating both its effectiveness and efficiency.
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。
