Departments of Radiology.
Human Oncology, School of Medicine and Public Health, University of Wisconsin, Madison, Wisconsin.
Pract Radiat Oncol. 2022 Jan-Feb;12(1):e40-e48. doi: 10.1016/j.prro.2021.08.007. Epub 2021 Aug 24.
Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast, which makes it useful for delineating tumor and normal structures in radiation therapy planning, but MRI cannot readily provide electron density for dose calculation. Computed tomography (CT) is used but introduces registration uncertainty between MRI and CT. Previous studies have shown that synthetic CTs (sCTs) can be generated directly from MRI images with deep learning methods. However, mainly high-field MRI images have been validated. This study tested whether acceptable sCTs for MR-only radiation therapy planning can be synthesized using an integrated MR-guided linear accelerator at 0.35T, using MRI images and treatment plans in the liver region.
Two models were investigated in this study: a convolutional neural network (Unet) with conventional mean square error (MSE) loss and a Unet using a secondary convolutional neural network for perceptual loss. A total of 37 cases were used in this study with 10-fold cross validation, and 37 treatment plans were generated and evaluated for target coverage and dose to organs at risk (OARs) in the MSE loss model, perceptual loss model, and original CT.
The sCTs predicted by the perceptual loss model had improved subjective visual quality compared with those predicted by the MSE loss model, but both were similar in mean absolute error (MAE), peak-signal-to-noise ratio (PSNR), and normalized cross-correlation (NCC). The MAE, PSNR, and NCC for the perceptual loss model were 35.64, 24.11, and 0.9539, respectively, and those for the MSE loss model were 35.67, 24.36, and 0.9566, respectively. No significant differences in target coverage and dose to OARs were found between the sCT predicted by the perceptual loss model or by the MSE model and the original CT image.
This study indicated that a Unet with both MSE loss and perceptual loss models can be used for generating sCT images from a 0.35T integrated MR linear accelerator.
磁共振成像（MRI）提供了出色的软组织对比度，这使其在放射治疗计划中用于描绘肿瘤和正常结构非常有用，但 MRI 不能轻易提供用于剂量计算的电子密度。因此，计算机断层扫描（CT）被用于此目的，但会在 MRI 和 CT 之间引入配准不确定性。先前的研究表明，可以使用深度学习方法直接从 MRI 图像生成合成 CT（sCT）。然而，这些研究主要验证了高磁场 MRI 图像。本研究测试了是否可以使用集成的 0.35T 磁共振引导线性加速器，基于 MRI 图像和肝脏区域的治疗计划，合成用于仅接受 MRI 放疗计划的可接受的 sCT。
本研究中研究了两种模型：具有传统均方误差（MSE）损失的卷积神经网络（Unet）和使用二次卷积神经网络进行感知损失的 Unet。本研究共使用了 37 例病例，并进行了 10 折交叉验证，共生成并评估了 37 种治疗计划，以评估 MSE 损失模型、感知损失模型和原始 CT 中的靶区覆盖和危及器官（OAR）剂量。
与 MSE 损失模型预测的 sCT 相比，感知损失模型预测的 sCT 具有改善的主观视觉质量，但在平均绝对误差（MAE）、峰值信噪比（PSNR）和归一化互相关（NCC）方面两者相似。感知损失模型的 MAE、PSNR 和 NCC 分别为 35.64、24.11 和 0.9539，而 MSE 损失模型的 MAE、PSNR 和 NCC 分别为 35.67、24.36 和 0.9566。在靶区覆盖和 OAR 剂量方面，感知损失模型或 MSE 模型预测的 sCT 与原始 CT 图像之间没有显著差异。
本研究表明，具有 MSE 损失和感知损失模型的 Unet 可用于从 0.35T 集成的磁共振线性加速器生成 sCT 图像。
