基于模块化数据驱动的重建框架，用于消除 CT 中非理想焦点效应。

Department of Radiation Oncology, Stanford University, Stanford, CA, USA.

Med Phys. 2021 May;48(5):2245-2257. doi: 10.1002/mp.14785. Epub 2021 Mar 23.

PURPOSE

High-performance computed tomography (CT) plays a vital role in clinical decision-making. However, the performance of CT imaging is adversely affected by the nonideal focal spot size of the x-ray source or degraded by an enlarged focal spot size due to aging. In this work, we aim to develop a deep learning-based strategy to mitigate the problem so that high spatial resolution CT images can be obtained even in the case of a nonideal x-ray source.

METHODS

To reconstruct high-quality CT images from blurred sinograms via joint image and sinogram learning, a cross-domain hybrid model is formulated via deep learning into a modularized data-driven reconstruction (MDR) framework. The proposed MDR framework comprises several blocks, and all the blocks share the same network architecture and network parameters. In essence, each block utilizes two sub-models to generate an estimated blur kernel and a high-quality CT image simultaneously. In this way, our framework generates not only a final high-quality CT image but also a series of intermediate images with gradually improved anatomical details, enhancing the visual perception for clinicians through the dynamic process. We used simulated training datasets to train our model in an end-to-end manner and tested our model on both simulated and realistic experimental datasets.

RESULTS

On the simulated testing datasets, our approach increases the information fidelity criterion (IFC) by up to 34.2%, the universal quality index (UQI) by up to 20.3%, the signal-to-noise (SNR) by up to 6.7%, and reduces the root mean square error (RMSE) by up to 10.5% as compared with FBP. Compared with the iterative deconvolution method (NSM), MDR increases IFC by up to 24.7%, UQI by up to 16.7%, SNR by up to 6.0%, and reduces RMSE by up to 9.4%. In the modulation transfer function (MTF) experiment, our method improves the MTF by 34.5% and MTF by 18.7% as compared with FBP, Similarly remarkably, our method improves MTF by 14.3% and MTF by 0.9% as compared with NSM. Also, our method shows better imaging results in the edge of bony structures and other tiny structures in the experiments using phantom consisting of ham and a bottle of peanuts.

CONCLUSIONS

A modularized data-driven CT reconstruction framework is established to mitigate the blurring effect caused by a nonideal x-ray source with relatively large focal spot. The proposed method enables us to obtain high-resolution images with less ideal x-ray source.

目的

高性能计算机断层扫描（CT）在临床决策中起着至关重要的作用。然而，由于射线源的非理想焦点尺寸或由于老化导致焦点尺寸增大，CT 成像的性能会受到不利影响。在这项工作中，我们旨在开发一种基于深度学习的策略来解决这个问题，以便即使在非理想射线源的情况下，也能获得高空间分辨率的 CT 图像。

方法

为了通过联合图像和正弦图学习从模糊的正弦图中重建高质量的 CT 图像，通过深度学习将一个跨域混合模型构建到模块化数据驱动重建（MDR）框架中。所提出的 MDR 框架由几个块组成，所有块都共享相同的网络架构和网络参数。从本质上讲，每个块利用两个子模型来同时生成估计的模糊核和高质量的 CT 图像。通过这种方式，我们的框架不仅生成最终的高质量 CT 图像，还生成一系列具有逐渐改善的解剖细节的中间图像，通过动态过程增强临床医生的视觉感知。我们使用模拟训练数据集以端到端的方式训练我们的模型，并在模拟和真实实验数据集上测试我们的模型。

结果

在模拟测试数据集上，与 FBP 相比，我们的方法将信息保真度准则（IFC）提高了高达 34.2%，通用质量指数（UQI）提高了高达 20.3%，信噪比（SNR）提高了高达 6.7%，均方根误差（RMSE）降低了高达 10.5%。与迭代去卷积方法（NSM）相比，MDR 将 IFC 提高了高达 24.7%，UQI 提高了高达 16.7%，SNR 提高了高达 6.0%，RMSE 降低了高达 9.4%。在调制传递函数（MTF）实验中，与 FBP 相比，我们的方法将 MTF 提高了 34.5%，MTF 提高了 18.7%。同样显著的是，与 NSM 相比，我们的方法将 MTF 提高了 14.3%，MTF 提高了 0.9%。此外，我们的方法在使用由火腿和一瓶花生组成的幻影进行的实验中，在骨结构和其他微小结构的边缘显示出更好的成像结果。