Li Haoran, Tsai Yun-Han, Liu Hengjie, Ruan Dan
Department of Bioengineering, University of California Los Angeles, Los Angeles, California, USA.
Graduate Program of Physics and Biology in Medicine, University of California, Los Angeles, Los Angeles, California, USA.
Med Phys. 2024 Dec;51(12):8828-8835. doi: 10.1002/mp.17435. Epub 2024 Oct 1.
Cone beam computed tomography (CBCT) is a widely available modality, but its clinical utility has been limited by low detail conspicuity and quantitative accuracy. Convenient post-reconstruction denoising is subject to back projected patterned residual, but joint denoise-reconstruction is typically computationally expensive and complex.
In this study, we develop and evaluate a novel Metric-learning guided wavelet transform reconstruction (MEGATRON) approach to enhance image domain quality with projection-domain processing.
Projection domain based processing has the benefit of being simple, efficient, and compatible with various reconstruction toolkit and vendor platforms. However, they also typically show inferior performance in the final reconstructed image, because the denoising goals in projection and image domains do not necessarily align. Motivated by these observations, this work aims to translate the demand for quality enhancement from the quantitative image domain to the more easily operable projection domain. Specifically, the proposed paradigm consists of a metric learning module and a denoising network module. Via metric learning, enhancement objectives on the wavelet encoded sinogram domain data are defined to reflect post-reconstruction image discrepancy. The denoising network maps measured cone-beam projection to its enhanced version, driven by the learnt objective. In doing so, the denoiser operates in the convenient sinogram to sinogram fashion but reflects improvement in reconstructed image as the final goal. Implementation-wise, metric learning was formalized as optimizing the weighted fitting of wavelet subbands, and a res-Unet, which is a Unet structure with residual blocks, was used for denoising. To access quantitative reference, cone-beam projections were simulated using the X-ray based Cancer Imaging Simulation Toolkit (XCIST). In both learning modules, a data set of 123 human thoraxes, which was from Open-Source Imaging Consortium (OSIC) Pulmonary Fibrosis Progression challenge, was used. Reconstructed CBCT thoracic images were compared against ground truth FB and performance was assessed in root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM).
MEGATRON achieved RMSE in HU value, PSNR, and SSIM were 30.97 ± 4.25, 37.45 ± 1.78, and 93.23 ± 1.62, respectively. These values are on par with reported results from sophisticated physics-driven CBCT enhancement, demonstrating promise and utility of the proposed MEGATRON method.
We have demonstrated that incorporating the proposed metric learning into sinogram denoising introduces awareness of reconstruction goal and improves final quantitative performance. The proposed approach is compatible with a wide range of denoiser network structures and reconstruction modules, to suit customized need or further improve performance.
锥形束计算机断层扫描（CBCT）是一种广泛应用的成像方式，但其临床效用受到低细节清晰度和定量准确性的限制。便捷的重建后去噪容易出现反投影图案残留，但联合去噪 - 重建通常计算成本高且复杂。
在本研究中，我们开发并评估一种新型的度量学习引导小波变换重建（MEGATRON）方法，通过投影域处理来提高图像域质量。
基于投影域的处理具有简单、高效且与各种重建工具包和供应商平台兼容的优点。然而，它们在最终重建图像中的性能通常也较差，因为投影域和图像域中的去噪目标不一定一致。基于这些观察结果，这项工作旨在将质量增强的需求从定量图像域转换到更易于操作的投影域。具体而言，所提出的范式由一个度量学习模块和一个去噪网络模块组成。通过度量学习，在小波编码的正弦图域数据上定义增强目标，以反映重建后图像的差异。去噪网络将测量的锥形束投影映射到其增强版本，由学习到的目标驱动。这样，去噪器以方便的正弦图到正弦图的方式运行，但以重建图像的改进作为最终目标。在实现方面，度量学习被形式化为优化小波子带的加权拟合，并使用带有残差块的Unet结构（res - Unet）进行去噪。为了获得定量参考，使用基于X射线的癌症成像模拟工具包（XCIST）模拟锥形束投影。在两个学习模块中，使用了来自开源成像联盟（OSIC）肺纤维化进展挑战的123例人体胸部数据集。将重建的CBCT胸部图像与真实的FB进行比较，并通过均方根误差（RMSE）、峰值信噪比（PSNR）和结构相似性指数（SSIM）评估性能。
MEGATRON在HU值、PSNR和SSIM方面实现的RMSE分别为30.97±4.25、37.45±1.78和93.23±1.62。这些值与复杂的物理驱动CBCT增强的报告结果相当，证明了所提出的MEGATRON方法的前景和效用。
我们已经证明，将所提出的度量学习纳入正弦图去噪可引入对重建目标的认识并提高最终的定量性能。所提出的方法与广泛的去噪器网络结构和重建模块兼容，以满足定制需求或进一步提高性能。
