Kim Mimi, Kim Jong Soo, Lee Changhwan, Kang Bo-Kyeong
Department of Radiology, Hanyang University Seoul Hospital, Seoul, Republic of Korea.
Institute for Software Convergence, Hanyang University, Seoul, Republic of Korea.
Eur J Radiol Open. 2020 Dec 21;8:100316. doi: 10.1016/j.ejro.2020.100316. eCollection 2021.
BACKGROUND/PURPOSE: The purpose of this study was to assess the diagnostic performance of artificial neural networks (ANNs) to detect pneumoperitoneum in abdominal radiographs for the first time.
This approach applied a novel deep-learning algorithm, a simple ANN training process without employing a convolution neural network (CNN), and also used a widely utilized deep-learning method, ResNet-50, for comparison.
By applying ResNet-50 to abdominal radiographs, we obtained an area under the ROC curve (AUC) of 0.916 and an accuracy of 85.0 % with a sensitivity of 85.7 % and a predictive value of the negative tests (NPV) of 91.7 %. Compared with the most commonly applied deep-learning methods such as a CNN, our novel approach used extremely small ANN structures and a simple ANN training process. The diagnostic performance of our approach, with a sensitivity of 88.6 % and NPV of 91.3 %, was compared decently with that of ResNet-50.
The results of this study showed that ANN-based computer-assisted diagnostics can be used to accurately detect pneumoperitoneum in abdominal radiographs, reduce the time delay in diagnosing urgent diseases such as pneumoperitoneum, and increase the effectiveness of clinical practice and patient care.
背景/目的：本研究的目的是首次评估人工神经网络（ANN）在腹部X光片中检测气腹的诊断性能。
该方法应用了一种新颖的深度学习算法，一种不采用卷积神经网络（CNN）的简单ANN训练过程，并且还使用了一种广泛使用的深度学习方法ResNet-50进行比较。
通过将ResNet-50应用于腹部X光片，我们获得了受试者工作特征曲线下面积（AUC）为0.916，准确率为85.0%，灵敏度为85.7%，阴性试验预测值（NPV）为91.7%。与最常用的深度学习方法如CNN相比，我们的新方法使用了极小的ANN结构和简单的ANN训练过程。我们方法的诊断性能，灵敏度为88.6%，NPV为91.3%，与ResNet-50相比表现良好。
本研究结果表明，基于ANN的计算机辅助诊断可用于准确检测腹部X光片中的气腹，减少诊断气腹等紧急疾病的时间延迟，并提高临床实践和患者护理的有效性。
