The University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences, Houston, TX, USA.
Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
J Appl Clin Med Phys. 2021 May;22(5):168-174. doi: 10.1002/acm2.13207. Epub 2021 Mar 29.
To investigate the impact of computed tomography (CT) image acquisition and reconstruction parameters, including slice thickness, pixel size, and dose, on automatic contouring algorithms.
Eleven scans from patients with head-and-neck cancer were reconstructed with varying slice thicknesses and pixel sizes. CT dose was varied by adding noise using low-dose simulation software. The impact of these imaging parameters on two in-house auto-contouring algorithms, one convolutional neural network (CNN)-based and one multiatlas-based system (MACS) was investigated for 183 reconstructed scans. For each algorithm, auto-contours for organs-at-risk were compared with auto-contours from scans with 3 mm slice thickness, 0.977 mm pixel size, and 100% CT dose using Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD).
Increasing the slice thickness from baseline value of 3 mm gave a progressive reduction in DSC and an increase in HD and MSD on average for all structures. Reducing the CT dose only had a relatively minimal effect on DSC and HD. The rate of change with respect to dose for both auto-contouring methods is approximately 0. Changes in pixel size had a small effect on DSC and HD for CNN-based auto-contouring with differences in DSC being within 0.07. Small structures had larger deviations from the baseline values than large structures for DSC. The relative differences in HD and MSD between the large and small structures were small.
Auto-contours can deviate substantially with changes in CT acquisition and reconstruction parameters, especially slice thickness and pixel size. The CNN was less sensitive to changes in pixel size, and dose levels than the MACS. The results contraindicated more restrictive values for the parameters should be used than a typical imaging protocol for head-and-neck.
研究 CT 图像采集和重建参数（包括层厚、像素大小和剂量）对自动勾画算法的影响。
对 11 例头颈部癌症患者的扫描进行了不同层厚和像素大小的重建。使用低剂量模拟软件通过添加噪声来改变 CT 剂量。研究了这些成像参数对两种内部自动勾画算法（一种基于卷积神经网络（CNN）的算法和一种基于多图谱的系统（MACS））的影响，对 183 个重建扫描进行了研究。对于每个算法，使用 Dice 相似系数（DSC）、Hausdorff 距离（HD）和平均表面距离（MSD）将危及器官的自动轮廓与 3mm 层厚、0.977mm 像素大小和 100%CT 剂量的扫描的自动轮廓进行比较。
与基线 3mm 层厚相比，增加层厚会导致所有结构的 DSC 逐渐降低，HD 和 MSD 增加。仅降低 CT 剂量对 DSC 和 HD 的影响相对较小。对于两种自动勾画方法，剂量变化的变化率约为 0.01。基于 CNN 的自动勾画的像素大小变化对 DSC 和 HD 的影响较小，DSC 的差异在 0.07 以内。小结构的 DSC 与基线值的偏差大于大结构的偏差。大结构和小结构之间的 HD 和 MSD 的相对差异较小。
自动勾画会随着 CT 采集和重建参数的变化而发生显著变化，尤其是层厚和像素大小。与 MACS 相比，CNN 对像素大小和剂量变化的敏感性较低。结果表明，与典型的头颈部成像方案相比，应该使用比参数更具限制性的值。
