当前位置: X-MOL 学术Phys. Med. Biol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Synthetic CT generation from CBCT images via unsupervised deep learning
Physics in Medicine & Biology ( IF 3.5 ) Pub Date : 2021-06-01 , DOI: 10.1088/1361-6560/ac01b6
Liyuan Chen 1 , Xiao Liang 1 , Chenyang Shen 1 , Dan Nguyen 1 , Steve Jiang 1 , Jing Wang 1
Affiliation  

Adaptive-radiation-therapy (ART) is applied to account for anatomical variations observed over the treatment course. Daily or weekly cone-beam computed tomography (CBCT) is commonly used in clinic for patient positioning, but CBCT’s inaccuracy in Hounsfield units (HU) prevents its application to dose calculation and treatment planning. Adaptive re-planning can be performed by deformably registering planning CT (pCT) to CBCT. However, scattering artifacts and noise in CBCT decrease the accuracy of deformable registration and induce uncertainty in treatment plan. Hence, generating from CBCT a synthetic CT (sCT) that has the same anatomical structure as CBCT but accurate HU values is desirable for ART. We proposed an unsupervised style-transfer-based approach to generate sCT based on CBCT and pCT. Unsupervised learning was desired because exactly matched CBCT and CT are rarely available, even when they are taken a few minutes apart. In the proposed model, CBCT and pCT are two inputs that provide anatomical structure and accurate HU information, respectively. The training objective function is designed to simultaneously minimize (1) contextual loss between sCT and CBCT to maintain the content and structure of CBCT in sCT and (2) style loss between sCT and pCT to achieve pCT-like image quality in sCT. We used CBCT and pCT images of 114 patients to train and validate the designed model, and another 29 independent patient cases to test the model’s effectiveness. We quantitatively compared the resulting sCT with the original CBCT using the deformed same-day pCT as reference. Structure-similarity-index, peak-signal-to-noise-ratio, and mean-absolute-error in HU of sCT were 0.9723, 33.68, and 28.52, respectively, while those of CBCT were 0.9182, 29.67, and 49.90, respectively. We have demonstrated the effectiveness of the proposed model in using CBCT and pCT to synthesize CT-quality images. This model may permit using CBCT for advanced applications such as adaptive treatment planning.



中文翻译:

通过无监督深度学习从 CBCT 图像生成合成 CT

适应性放射治疗 (ART) 用于解释在治疗过程中观察到的解剖结构变化。每日或每周锥形束计算机断层扫描 (CBCT) 在临床中通常用于患者定位,但 CBCT 在 Hounsfield 单位 (HU) 中的不准确性阻碍了其应用于剂量计算和治疗计划。自适应重新规划可以通过将规划 CT (pCT) 可变形地配准到 CBCT 来执行。然而,CBCT 中的散射伪影和噪声会降低可变形配准的准确性并导致治疗计划的不确定性。因此,从 CBCT 生成具有与 CBCT 相同的解剖结构但准确的 HU 值的合成 CT (sCT) 是 ART 所希望的。我们提出了一种基于无监督风格转移的方法来生成基于 CBCT 和 pCT 的 sCT。需要无监督学习,因为精确匹配的 CBCT 和 CT 很少可用,即使它们相隔几分钟也是如此。在提出的模型中,CBCT 和 pCT 是两个输入,分别提供解剖结构和准确的 HU 信息。训练目标函数旨在同时最小化 (1) sCT 和 CBCT 之间的上下文损失,以保持 sCT 中 CBCT 的内容和结构,以及 (2) sCT 和 pCT 之间的样式损失,以在 sCT 中实现类似 pCT 的图像质量。我们使用 114 名患者的 CBCT 和 pCT 图像来训练和验证设计的模型,并使用另外 29 个独立的患者病例来测试模型的有效性。我们使用变形的当天 pCT 作为参考,将得到的 sCT 与原始 CBCT 进行了定量比较。结构相似性指数,峰值信噪比,sCT 的 HU 和平均绝对误差分别为 0.9723、33.68 和 28.52,而 CBCT 的分别为 0.9182、29.67 和 49.90。我们已经证明了所提出的模型在使用 CBCT 和 pCT 合成 CT 质量图像方面的有效性。该模型可能允许将 CBCT 用于高级应用,例如自适应治疗计划。

更新日期:2021-06-01
down
wechat
bug