Speckle noise has long been an extensively studied problem in medical imaging. In recent years, there have been significant advances in leveraging deep learning methods for noise reduction. Nevertheless, adaptation of supervised learning models to unseen domains remains a challenging problem. Specifically, deep neural networks (DNNs) trained for computational imaging tasks are vulnerable to changes in the acquisition system's physical parameters, such as: sampling space, resolution, and contrast. Even within the same acquisition system, performance degrades across datasets of different biological tissues. In this work, we propose a few-shot supervised learning framework for optical coherence tomography (OCT) noise reduction, that offers a dramatic increase in training speed and requires only a single image, or part of an image, and a corresponding speckle suppressed ground truth, for training. Furthermore, we formulate the domain shift problem for OCT diverse imaging systems, and prove that the output resolution of a despeckling trained model is determined by the source domain resolution. We also provide possible remedies. We propose different practical implementations of our approach, verify and compare their applicability, robustness, and computational efficiency. Our results demonstrate significant potential for generally improving sample complexity, generalization, and time efficiency, for coherent and non-coherent noise reduction via supervised learning models, that can also be leveraged for other real-time computer vision applications.

翻译：散斑噪声一直是医学成像中广泛研究的问题。近年来，利用深度学习方法进行降噪取得了显著进展。然而，监督学习模型对未知域的适应仍是一个具有挑战性的问题。具体来说，为计算成像任务训练的深度神经网络（DNNs）对采集系统物理参数的变化（如采样空间、分辨率和对比度）非常敏感。即使在同一采集系统内，不同生物组织数据集上的性能也会下降。在这项工作中，我们提出了一种用于光学相干断层扫描（OCT）降噪的少样本监督学习框架，该框架显著提高了训练速度，且仅需单张图像（或图像的一部分）以及对应的散斑抑制真值即可进行训练。此外，我们针对OCT不同成像系统形式化定义了域偏移问题，并证明了经过去散斑训练的模型的输出分辨率由源域分辨率决定，同时提供了可能的解决方案。我们提出了该方法的不同实际实现方式，验证并比较了其适用性、鲁棒性和计算效率。我们的结果表明，该方法在通过监督学习模型实现相干与非相干噪声降噪方面，具有显著提升样本复杂度、泛化能力和时间效率的潜力，且可进一步推广至其他实时计算机视觉应用。