Division of Medical Physics, Department of Information Technology and Medical Engineering, Human Health Sciences, Graduate School of Medicine, Kyoto University, 53 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, 606-8507, Japan.
Department of Radiation Oncology and Image-Applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
Radiat Oncol. 2021 Jun 6;16(1):96. doi: 10.1186/s13014-021-01827-0.
We investigated the geometric and dosimetric impact of three-dimensional (3D) generative adversarial network (GAN)-based metal artifact reduction (MAR) algorithms on volumetric-modulated arc therapy (VMAT) and intensity-modulated proton therapy (IMPT) for the head and neck region, based on artifact-free computed tomography (CT) volumes with dental fillings.
Thirteen metal-free CT volumes of the head and neck regions were obtained from The Cancer Imaging Archive. To simulate metal artifacts on CT volumes, we defined 3D regions of the teeth for pseudo-dental fillings from the metal-free CT volumes. HU values of 4000 HU were assigned to the selected teeth region of interest. Two different CT volumes, one with four (m4) and the other with eight (m8) pseudo-dental fillings, were generated for each case. These CT volumes were used as the Reference. CT volumes with metal artifacts were then generated from the Reference CT volumes (Artifacts). On the Artifacts CT volumes, metal artifacts were manually corrected for using the water density override method with a value of 1.0 g/cm (Water). By contrast, the CT volumes with reduced metal artifacts using 3D GAN model extension of CycleGAN were also generated (GAN-MAR). The structural similarity (SSIM) index within the planning target volume was calculated as quantitative error metric between the Reference CT volumes and the other volumes. After creating VMAT and IMPT plans on the Reference CT volumes, the reference plans were recalculated for the remaining CT volumes.
The time required to generate a single GAN-MAR CT volume was approximately 30 s. The median SSIMs were lower in the m8 group than those in the m4 group, and ANOVA showed a significant difference in the SSIM for the m8 group (p < 0.05). Although the median differences in D, D and D were larger in the m8 group than the m4 group, those from the reference plans were within 3% for VMAT and 1% for IMPT.
The GAN-MAR CT volumes generated in a short time were closer to the Reference CT volumes than the Water and Artifacts CT volumes. The observed dosimetric differences compared to the reference plan were clinically acceptable.
我们研究了基于三维（3D）生成对抗网络（GAN）的金属伪影减少（MAR）算法对有牙科填充物的头部和颈部区域的容积调制弧形治疗（VMAT）和强度调制质子治疗（IMPT）的几何和剂量学影响，这些算法基于无金属伪影的计算机断层扫描（CT）容积。
从癌症影像档案中获得 13 个头部和颈部无金属的 CT 容积。为了在 CT 容积上模拟金属伪影，我们从无金属 CT 容积中定义了牙齿的三维区域作为伪牙科填充物。选定的牙齿感兴趣区域的 HU 值被分配为 4000 HU。为每个病例生成两个不同的 CT 容积，一个有四个（m4），另一个有八个（m8）伪牙科填充物。这些 CT 容积被用作参考（Reference）。然后从参考 CT 容积（Artifacts）生成带有金属伪影的 CT 容积。在 Artifacts CT 容积上，使用水密度覆盖方法手动校正金属伪影，其值为 1.0 g/cm（Water）。相比之下，还使用 CycleGAN 的 3D GAN 模型扩展生成了减少金属伪影的 CT 容积（GAN-MAR）。计划靶区（PTV）内的结构相似性（SSIM）指数被计算为参考 CT 容积和其他容积之间的定量误差指标。在参考 CT 容积上创建 VMAT 和 IMPT 计划后，剩余 CT 容积上的参考计划也被重新计算。
生成单个 GAN-MAR CT 容积大约需要 30 秒。m8 组的中位数 SSIM 低于 m4 组，方差分析显示 m8 组的 SSIM 存在显著差异（p < 0.05）。尽管 m8 组的 D、D 和 D 中位数差异大于 m4 组，但从参考计划来看，VMAT 的差异在 3%以内，IMPT 的差异在 1%以内。
在短时间内生成的 GAN-MAR CT 容积比 Water 和 Artifacts CT 容积更接近参考 CT 容积。与参考计划相比，观察到的剂量学差异在临床可接受范围内。
