Department of radiology, hôpital de la Croix-Rousse, 103, Grande rue de la Croix-Rousse, 69004 Lyon, France.
Unité CNRS UMR 5220, CREATIS, Inserm U1206, Insa Lyon, université Lyon 1, université Jean-Monnet Saint-Étienne, 7, avenue Jean-Capelle, 69100 Villeurbanne, France; Department of radiology, Louis-Pradel hospital, 59, boulevard Pinel, 69500 Bron, France.
Diagn Interv Imaging. 2019 Mar;100(3):177-183. doi: 10.1016/j.diii.2018.11.001. Epub 2018 Nov 27.
The purpose of this study was to develop a convolutional neural network (CNN) to determine the extent of over-scanning in the Z-direction associated with lung computed tomography (CT) examinations.
The CT examinations of 250 patients were used to train the machine learning software and 100 were used to validate the results. Each lung CT examination was divided into cervical, lung, and abdominal areas by the CNN and 2 independent radiologists, and the length of each area was measured. Every part above or below the lung marks was labeled as over-scanning. The accuracy of the CNN was calculated after the training phase and agreement between CNN and radiologists was assessed using kappa statistics during the validation phase. After validation the software was used to estimate the length of each of the three areas and the total over-scanning in further 1000 patients.
An accuracy of 0.99 was found for the testing dataset and a very good agreement (kappa=0.98) between the CNN and the radiologists' evaluation was found for the validation dataset. Over-scanning was 22.8% with the CNN and 22.2% with the radiologists. The degree of over-scanning was 22.6% in 1000 lung CT examinations.
Our study shows a substantial over estimation of the length of the area to be scanned during lung CT and thus an unnecessary patient's over-exposure to ionizing radiation. This over-scanning can be assessed easily, reliably and quickly using CNN.
本研究旨在开发卷积神经网络（CNN）以确定与肺部计算机断层扫描（CT）检查相关的 Z 方向过度扫描的程度。
使用 250 名患者的 CT 检查来训练机器学习软件，并用 100 名患者来验证结果。每个肺部 CT 检查由 CNN 和 2 名独立放射科医生分为颈椎、肺部和腹部区域，并测量每个区域的长度。肺部标记上方或下方的每个部位均标记为过度扫描。在训练阶段后计算 CNN 的准确性，并在验证阶段使用 Kappa 统计评估 CNN 和放射科医生之间的一致性。验证后，该软件用于估计另外 1000 名患者的三个区域中的每一个的长度和总过度扫描。
测试数据集的准确率为 0.99，验证数据集的 CNN 和放射科医生评估之间存在非常好的一致性（kappa=0.98）。CNN 发现过度扫描为 22.8%，放射科医生为 22.2%。1000 次肺部 CT 检查中过度扫描的程度为 22.6%。
我们的研究表明，在肺部 CT 期间扫描区域的长度存在大量高估，从而导致患者不必要地暴露于电离辐射。使用 CNN 可以轻松、可靠、快速地评估这种过度扫描。
