HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, P.O. Box 340, FI-00029 HUS, Helsinki, Finland; Department of Physics, University of Helsinki, P.O. Box 64, FI-00014 Helsinki, Finland.
HUS Medical Imaging Center, Radiology, University of Helsinki and Helsinki University Hospital, P.O. Box 340, FI-00029 HUS, Helsinki, Finland.
Phys Med. 2021 Mar;83:138-145. doi: 10.1016/j.ejmp.2021.03.014. Epub 2021 Mar 23.
To automate diagnostic chest radiograph imaging quality control (lung inclusion at all four edges, patient rotation, and correct inspiration) using convolutional neural network models.
The data comprised of 2589 postero-anterior chest radiographs imaged in a standing position, which were divided into train, validation, and test sets. We increased the number of images for the inclusion by cropping appropriate images, and for the inclusion and the rotation by flipping the images horizontally. The image histograms were equalized, and the images were resized to a 512 × 512 resolution. We trained six convolutional neural networks models to detect the image quality features using manual image annotations as training targets. Additionally, we studied the inter-observer variability of the image annotation.
The convolutional neural networks' areas under the receiver operating characteristic curve were >0.88 for the inclusions, and >0.70 and >0.79 for the rotation and the inspiration, respectively. The inter-observer agreement between two human annotators for the assessed image-quality features were: 92%, 90%, 82%, and 88% for the inclusion at patient's left, patient's right, cranial, and caudal edges, and 78% and 89% for the rotation and inspiration, respectively. Higher inter-observer agreement was related to a smaller variance in the network confidence.
The developed models provide automated tools for the quality control in a radiological department. Additionally, the convolutional neural networks could be used to obtain immediate feedback of the chest radiograph image quality, which could serve as an educational instrument.
使用卷积神经网络模型实现诊断性胸部 X 光成像质量控制（包括四个边缘的肺野、患者旋转和正确吸气）的自动化。
该数据包含 2589 张站立位后前位胸部 X 光片，分为训练集、验证集和测试集。我们通过裁剪合适的图像来增加包括在内的图像数量，通过水平翻转图像来增加包括和旋转的图像数量。对图像直方图进行均衡化，并将图像调整为 512×512 的分辨率。我们使用手动图像注释作为训练目标，训练了六个卷积神经网络模型来检测图像质量特征。此外，我们还研究了图像注释的观察者间变异性。
卷积神经网络的接收者操作特征曲线下面积（area under the receiver operating characteristic curve，AUC）对于包含的情况大于 0.88，对于旋转和吸气的情况分别大于 0.70 和 0.79。两位人类注释员对评估图像质量特征的观察者间一致性为：对于患者左侧、右侧、颅侧和尾侧边缘的包含情况分别为 92%、90%、82%和 88%，对于旋转和吸气的情况分别为 78%和 89%。观察者间一致性较高与网络置信度的方差较小有关。
所开发的模型为放射科的质量控制提供了自动化工具。此外，卷积神经网络可用于获得胸部 X 光图像质量的即时反馈，可作为一种教育工具。
