Edward B. Singleton Department of Radiology, Division of Body Imaging, Texas Children's Hospital and Baylor College of Medicine, 6701 Fannin St. Suite 470, Houston, TX, 77030, USA.
Department of Radiology, Children's Hospital Los Angeles and Keck School of Medicine, University of Southern California, Los Angeles, CA, USA.
Eur J Pediatr. 2023 Nov;182(11):5159-5165. doi: 10.1007/s00431-023-05194-8. Epub 2023 Sep 12.
The combination of low dose CT and AI performance in the pediatric population has not been explored. Understanding this relationship is relevant for pediatric patients given the potential radiation risks. Here, the objective was to determine the diagnostic performance of commercially available Computer Aided Detection (CAD) for pulmonary nodules in pediatric patients at simulated lower radiation doses. Retrospective chart review of 30 sequential patients between 12-18 years old who underwent a chest CT on the Siemens SOMATOM Force from December 20, 2021, to April 12, 2022. Simulated lower doses at 75%, 50%, and 25% were reconstructed in lung kernel at 3 mm slice thickness using ReconCT and imported to Syngo CT Lung CAD software for analysis. Two pediatric radiologists reviewed the full dose CTs to determine the reference read. Two other pediatric radiologists compared the Lung CAD results at 100% dose and each simulated lower dose level to the reference on a nodule by nodule basis. The sensitivity (Sn), positive predictive value (PPV), and McNemar test were used for comparison of Lung CAD performance based on dose. As reference standard, 109 nodules were identified by the two radiologists. At 100%, and simulated 75%, 50%, and 25% doses, lung CAD detected 60, 62, 58, and 62 nodules, respectively; 28, 28, 29, and 26 were true positive (Sn = 26%, 26%, 27%, 24%), 30, 32, 27, and 34 were false positive (PPV = 48%, 47%, 52%, 43%). No statistically significance difference of Lung CAD performance at different doses was found, with p-values of 1.0, 1.0, and 0.7 at simulated 75%, 50%, and 25% doses compared to standard dose.
The Lung CAD shows low sensitivity at all simulated lower doses for the detection of pulmonary nodules in this pediatric population. However, radiation dose may be reduced from standard without further compromise to the Lung CAD performance.
• High diagnostic performance of Lung CAD for detection of pulmonary nodules in adults. • Several imaging techniques are applied to reduce pediatric radiation dose.
• Low sensitivity at all simulated lower doses for the detection of pulmonary nodules in our pediatric population. • Radiation dose may be reduced from standard without further compromise to the Lung CAD performance.
确定在模拟低辐射剂量下，商业计算机辅助检测（CAD）在儿科患者肺部结节检测中的诊断性能。
回顾性分析 2021 年 12 月 20 日至 2022 年 4 月 12 日期间，30 名年龄在 12-18 岁之间的连续患者在西门子 SOMATOM Force 上进行的胸部 CT 检查。使用 ReconCT 在肺核中以 3mm 层厚重建模拟的低剂量，分别为 75%、50%和 25%，并将其导入 Syngo CT Lung CAD 软件进行分析。两名儿科放射科医生回顾了全剂量 CT，以确定参考阅读。另外两名儿科放射科医生比较了 Lung CAD 在 100%剂量和每个模拟低剂量水平与基于结节的参考的结果。基于剂量，使用灵敏度（Sn）、阳性预测值（PPV）和 McNemar 检验比较 Lung CAD 性能。作为参考标准，两位放射科医生确定了 109 个结节。在 100%、模拟 75%、50%和 25%剂量下，Lung CAD 分别检测到 60、62、58 和 62 个结节；28、28、29 和 26 个为真阳性（Sn=26%、26%、27%、24%），30、32、27 和 34 个为假阳性（PPV=48%、47%、52%、43%）。在模拟 75%、50%和 25%剂量下，与标准剂量相比，Lung CAD 性能无统计学差异，p 值分别为 1.0、1.0 和 0.7。
在该儿科人群中，Lung CAD 在所有模拟低剂量下检测肺部结节的灵敏度均较低。然而，在不进一步影响 Lung CAD 性能的情况下，辐射剂量可能会从标准剂量降低。
需要注意的是，该研究存在一些局限性。首先，这是一项回顾性研究，因此存在选择偏差的可能性。其次，研究仅包括了一个中心的数据，因此结果可能不适用于其他机构。最后，由于研究中未包括非结节病变，因此无法评估 Lung CAD 在其他病变中的性能。
总之，该研究表明，在模拟低剂量下，Lung CAD 在检测儿科人群中的肺部结节时灵敏度较低。然而，在不进一步影响 Lung CAD 性能的情况下，辐射剂量可能会从标准剂量降低。
