Farjam Reza, Tyagi Neelam, Deasy Joseph O, Hunt Margie A
Department of Radiation Oncology, Weill Cornell Medicine/New York-Presbyterian Hospital, New York, NY, USA.
Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
J Appl Clin Med Phys. 2019 Jan;20(1):101-109. doi: 10.1002/acm2.12501. Epub 2018 Nov 26.
To investigate the potential of an atlas-based approach in generation of synthetic CT for pelvis anatomy.
Twenty-three matched pairs of computed tomography (CT) and magnetic resonance imaging (MRI) scans were selected from a pool of prostate cancer patients. All MR scans were preprocessed to reduce scanner- and patient-induced intensity inhomogeneities and to standardize their intensity histograms. Ten (training dataset) of 23 pairs were then utilized to construct the coregistered CT-MR atlas. The synthetic CT for a new patient is generated by appropriately weighting the deformed atlas of CT-MR onto the new patient MRI. The training dataset was used as an atlas to generate the synthetic CT for the rest of the patients (test dataset). The mean absolute error (MAE) between the deformed planning CT and synthetic CT was computed over the entire CT image, bone, fat, and muscle tissues. The original treatment plans were also recomputed on the new synthetic CTs and dose-volume histogram metrics were compared. The results were compared with a commercially available synthetic CT Software (MRCAT) that is routinely used in our clinic.
MAE errors (±SD) between the deformed planning CT and our proposed synthetic CTs in the test dataset were 47 ± 5, 116 ± 12, 36 ± 6, and 47 ± 5 HU for the entire image, bone, fat, and muscle tissues respectively. The MAEs were 65 ± 5, 172 ± 9, 43 ± 7, and 42 ± 4 HU for the corresponding tissues in MRCAT CT. The dosimetric comparison showed consistent results for all plans using our synthetic CT, deformed planning CT and MRCAT CT.
We investigated the potential of a multiatlas approach to generate synthetic CT images for the pelvis. Our results demonstrate excellent results in terms of HU value assignment compared to the original CT and dosimetric consistency.
研究基于图谱的方法在生成骨盆解剖结构合成CT方面的潜力。
从一组前列腺癌患者中选取23对匹配的计算机断层扫描（CT）和磁共振成像（MRI）扫描图像。所有MR扫描图像均经过预处理，以减少扫描仪和患者引起的强度不均匀性，并标准化其强度直方图。然后利用23对中的10对（训练数据集）构建配准的CT-MR图谱。通过将变形的CT-MR图谱适当加权到新患者的MRI上，为新患者生成合成CT。训练数据集用作图谱，为其余患者（测试数据集）生成合成CT。在整个CT图像、骨骼、脂肪和肌肉组织上计算变形的计划CT与合成CT之间的平均绝对误差（MAE）。还在新的合成CT上重新计算原始治疗计划，并比较剂量体积直方图指标。将结果与我们诊所常规使用的商用合成CT软件（MRCAT）进行比较。
在测试数据集中，变形的计划CT与我们提出的合成CT之间的MAE误差（±标准差）在整个图像、骨骼、脂肪和肌肉组织中分别为47±5、116±12、36±6和47±5 HU。MRCAT CT中相应组织的MAE分别为65±5、172±9、43±7和42±4 HU。剂量学比较显示，使用我们的合成CT、变形的计划CT和MRCAT CT的所有计划结果一致。
我们研究了多图谱方法生成骨盆合成CT图像的潜力。与原始CT相比，我们的结果在HU值分配和剂量学一致性方面显示出优异的结果。
