Biomedical Technology Services, Townsville University Hospital, Townsville, Australia.
School of Chemistry and Physics, Queensland University of Technology, Brisbane, Australia.
Phys Eng Sci Med. 2023 Sep;46(3):1321-1330. doi: 10.1007/s13246-023-01302-y. Epub 2023 Jul 18.
The patient setup technique currently in practice in most radiotherapy departments utilises on-couch cone-beam computed tomography (CBCT) imaging. Patients are positioned on the treatment couch using visual markers, followed by fine adjustments to the treatment couch position depending on the shift observed between the computed tomography (CT) image acquired for treatment planning and the CBCT image acquired immediately before commencing treatment. The field of view of CBCT images is limited to the size of the kV imager which leads to the acquisition of partial CBCT scans for lateralised tumors. The cone-beam geometry results in high amounts of streaking artifacts and in conjunction with limited anatomical information reduces the registration accuracy between planning CT and the CBCT image. This study proposes a methodology that can improve radiotherapy patient setup CBCT images by removing streaking artifacts and generating the missing patient anatomy with patient-specific precision. This research was split into two separate studies. In Study A, synthetic CBCT (sCBCT) data was created and used to train two machine learning models, one for removing streaking artifacts and the other for generating the missing patient anatomy. In Study B, planning CT and on-couch CBCT data from several patients was used to train a base model, from which a transfer of learning was performed using imagery from a single patient, producing a patient-specific model. The models developed for Study A performed well at removing streaking artifacts and generating the missing anatomy. The outputs yielded in Study B show that the model understands the individual patient and can generate the missing anatomy from partial CBCT datasets. The outputs generated demonstrate that there is utility in the proposed methodology which could improve the patient setup and ultimately lead to improving overall treatment quality.
目前大多数放射治疗部门采用的患者摆位技术是在治疗台上进行锥形束计算机断层扫描（CBCT）成像。患者首先使用视觉标记物定位在治疗台上，然后根据治疗计划中获取的 CT 图像与治疗前立即获取的 CBCT 图像之间的移位情况，对治疗台位置进行微调。CBCT 图像的视场仅限于千伏成像仪的大小，这导致对于侧方肿瘤只能采集部分 CBCT 扫描。由于锥形束几何形状导致大量条纹伪影，并且结合有限的解剖学信息，降低了计划 CT 与 CBCT 图像之间的配准准确性。本研究提出了一种可以改善放射治疗患者摆位 CBCT 图像的方法，通过去除条纹伪影并利用患者特异性精度生成缺失的患者解剖结构。这项研究分为两个独立的研究。在研究 A 中，创建了合成 CBCT（sCBCT）数据，并使用该数据训练了两个机器学习模型，一个用于去除条纹伪影，另一个用于生成缺失的患者解剖结构。在研究 B 中，使用了来自几个患者的计划 CT 和在治疗台上的 CBCT 数据来训练一个基础模型，然后使用单个患者的图像对该基础模型进行迁移学习，生成一个针对特定患者的模型。研究 A 中开发的模型在去除条纹伪影和生成缺失的解剖结构方面表现良好。研究 B 中的输出结果表明，该模型理解个体患者的情况，并能够从部分 CBCT 数据集生成缺失的解剖结构。生成的输出结果表明，所提出的方法具有一定的实用性，可以改善患者摆位，最终提高整体治疗质量。
