Peking University People's Hospital, Beijing, China.
Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China.
Radiat Oncol. 2024 Jul 9;19(1):89. doi: 10.1186/s13014-024-02467-w.
To investigate the feasibility of synthesizing computed tomography (CT) images from magnetic resonance (MR) images in multi-center datasets using generative adversarial networks (GANs) for rectal cancer MR-only radiotherapy.
Conventional T2-weighted MR and CT images were acquired from 90 rectal cancer patients at Peking University People's Hospital and 19 patients in public datasets. This study proposed a new model combining contrastive learning loss and consistency regularization loss to enhance the generalization of model for multi-center pelvic MRI-to-CT synthesis. The CT-to-sCT image similarity was evaluated by computing the mean absolute error (MAE), peak signal-to-noise ratio (SNRpeak), structural similarity index (SSIM) and Generalization Performance (GP). The dosimetric accuracy of synthetic CT was verified against CT-based dose distributions for the photon plan. Relative dose differences in the planning target volume and organs at risk were computed.
Our model presented excellent generalization with a GP of 0.911 on unseen datasets and outperformed the plain CycleGAN, where MAE decreased from 47.129 to 42.344, SNRpeak improved from 25.167 to 26.979, SSIM increased from 0.978 to 0.992. The dosimetric analysis demonstrated that most of the relative differences in dose and volume histogram (DVH) indicators between synthetic CT and real CT were less than 1%.
The proposed model can generate accurate synthetic CT in multi-center datasets from T2w-MR images. Most dosimetric differences were within clinically acceptable criteria for photon radiotherapy, demonstrating the feasibility of an MRI-only workflow for patients with rectal cancer.
为了研究使用生成对抗网络（GANs）在直肠癌 MR -only 放疗中从多中心数据集的磁共振（MR）图像合成计算断层扫描（CT）图像的可行性。
从北京大学人民医院的 90 例直肠癌患者和公共数据集的 19 例患者中采集了常规 T2 加权 MR 和 CT 图像。本研究提出了一种新的模型，该模型结合对比学习损失和一致性正则化损失，以增强模型对多中心骨盆 MRI-to-CT 合成的泛化能力。通过计算平均绝对误差（MAE）、峰值信噪比（SNRpeak）、结构相似性指数（SSIM）和泛化性能（GP）来评估 CT-to-sCT 图像相似度。验证了合成 CT 对光子计划的 CT 基剂量分布的剂量学准确性。计算了计划靶区和危及器官的相对剂量差异。
我们的模型在未见数据集上具有出色的泛化能力，GP 为 0.911，优于普通 CycleGAN，其中 MAE 从 47.129 降至 42.344，SNRpeak 从 25.167 提高至 26.979，SSIM 从 0.978 增加至 0.992。剂量学分析表明，合成 CT 和真实 CT 之间的剂量和体积直方图（DVH）指标的大多数相对差异小于 1%。
该模型可以从 T2w-MR 图像在多中心数据集生成准确的合成 CT。对于光子放疗，大多数剂量差异都在临床可接受的范围内，这表明对于直肠癌患者，仅使用 MRI 的工作流程是可行的。
