Low-dose computed tomography (CT) lung cancer screening is recommended by the US Preventive Services Task Force for high lung cancer-risk populations. In this study, we investigated an important factor affecting the CT dose-the scan length, for this CT exam. A neural network model based on the "UNET" framework was established to segment the lung region in the CT scout images. It was trained initially with 247 chest X-ray images and then with 40 CT scout images. The mean Intersection over Union (IOU) and Dice coefficient were reported to be 0.954 and 0.976, respectively. Lung scan boundaries were determined from this segmentation and compared with the boundaries marked by an expert for 150 validation images, resulting an average 4.7% difference. Seven hundred seventy CT low-dose lung screening exams were retrospectively analyzed with the validated model. The average "desired" scan length was 252 mm with a standard deviation of 28 mm. The average "over-range" was 58.5 mm or 24%. The upper boundary (superior) on average had an "over-range" of 17 mm, and the lower boundary (inferior) on average had an "over-range" of 41 mm. Further analysis of this data showed that the extent of "over-range" was independent of acquisition date, acquisition time, acquisition station, and patient age, but dependent on technologist and patient weight. We concluded that this machine learning method could effectively support quality control on the scan length for CT low-dose screening scans, enabling the eliminations of unnecessary patient dose.

中文翻译：

---

使用机器学习方法调查低剂量 CT 肺癌筛查扫描“超范围”问题。


美国预防服务工作组建议对肺癌高危人群进行低剂量计算机断层扫描 (CT) 肺癌筛查。在这项研究中，我们针对这次CT检查，研究了影响CT剂量的一个重要因素——扫描长度。建立了基于“UNET”框架的神经网络模型来分割CT侦察图像中的肺部区域。它最初使用 247 张胸部 X 射线图像进行训练，然后使用 40 张 CT 侦察图像进行训练。据报告，平均交并集 (IOU) 和 Dice 系数分别为 0.954 和 0.976。根据该分割确定肺部扫描边界，并与专家为 150 张验证图像标记的边界进行比较，得出平均 4.7% 的差异。使用经过验证的模型对 770 例 CT 低剂量肺部筛查检查进行回顾性分析。平均“所需”扫描长度为 252 毫米，标准偏差为 28 毫米。平均“超范围”为 58.5 毫米或 24%。上边界（上）平均“超出范围”为 17 毫米，下边界（下）平均“超出范围”为 41 毫米。对该数据的进一步分析表明，“超范围”的程度与采集日期、采集时间、采集站和患者年龄无关，但取决于技术人员和患者体重。我们的结论是，这种机器学习方法可以有效支持 CT 低剂量筛查扫描扫描长度的质量控制，从而消除不必要的患者剂量。