Pattern Recognition Lab, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, 91058, Germany.
Fraunhofer Institute for Ceramic Technologies and Systems IKTS, Forchheim, 91301, Germany.
Med Phys. 2022 Aug;49(8):5107-5120. doi: 10.1002/mp.15718. Epub 2022 May 30.
Computed tomography (CT) is widely used as an imaging tool to visualize three-dimensional structures with expressive bone-soft tissue contrast. However, CT resolution can be severely degraded through low-dose acquisitions, highlighting the importance of effective denoising algorithms.
Most data-driven denoising techniques are based on deep neural networks, and therefore, contain hundreds of thousands of trainable parameters, making them incomprehensible and prone to prediction failures. Developing understandable and robust denoising algorithms achieving state-of-the-art performance helps to minimize radiation dose while maintaining data integrity.
This work presents an open-source CT denoising framework based on the idea of bilateral filtering. We propose a bilateral filter that can be incorporated into any deep learning pipeline and optimized in a purely data-driven way by calculating the gradient flow toward its hyperparameters and its input. Denoising in pure image-to-image pipelines and across different domains such as raw detector data and reconstructed volume, using a differentiable backprojection layer, is demonstrated. In contrast to other models, our bilateral filter layer consists of only four trainable parameters and constrains the applied operation to follow the traditional bilateral filter algorithm by design.
Although only using three spatial parameters and one intensity range parameter per filter layer, the proposed denoising pipelines can compete with deep state-of-the-art denoising architectures with several hundred thousand parameters. Competitive denoising performance is achieved on x-ray microscope bone data and the 2016 Low Dose CT Grand Challenge data set. We report structural similarity index measures of 0.7094 and 0.9674 and peak signal-to-noise ratio values of 33.17 and 43.07 on the respective data sets.
Due to the extremely low number of trainable parameters with well-defined effect, prediction reliance and data integrity is guaranteed at any time in the proposed pipelines, in contrast to most other deep learning-based denoising architectures.
计算机断层扫描（CT）广泛用作可视化具有表达性骨软组织对比度的三维结构的成像工具。然而，通过低剂量采集，CT 分辨率可能会严重降低，这凸显了有效去噪算法的重要性。
大多数基于数据的去噪技术都是基于深度神经网络的，因此包含数十万可训练参数，这使得它们难以理解且容易出现预测失败。开发可理解且稳健的去噪算法，以实现最先进的性能，有助于在保持数据完整性的同时最小化辐射剂量。
这项工作提出了一种基于双边滤波思想的开源 CT 去噪框架。我们提出了一种双边滤波器，可以将其整合到任何深度学习管道中，并通过计算其超参数和输入的梯度流，以纯数据驱动的方式进行优化。演示了在纯图像到图像管道以及不同域（例如原始探测器数据和重建体积）中的去噪，使用可微分的反向投影层。与其他模型不同，我们的双边滤波器层仅由四个可训练参数组成，并通过设计将应用的操作限制为遵循传统的双边滤波器算法。
尽管每个滤波器层仅使用三个空间参数和一个强度范围参数，但所提出的去噪管道可以与具有数十万参数的深度最先进的去噪架构竞争。在 X 射线显微镜骨数据和 2016 年低剂量 CT 大挑战数据集上实现了具有竞争力的去噪性能。我们分别报告了在各自数据集上的结构相似性指数测量值为 0.7094 和 0.9674，以及峰值信噪比值为 33.17 和 43.07。
由于具有定义明确效果的可训练参数数量非常少，因此在提出的管道中，任何时候都可以保证预测的可靠性和数据的完整性，这与大多数其他基于深度学习的去噪架构形成对比。
