[Application of a light-weighted convolutional neural network for automatic recognition of coal workers' pneumoconiosis in the early stage].

Objective: To construct and verify a light-weighted convolutional neural network (CNN), and explore its application value for screening the early stage (subcategory 0/1 and stage Ⅰ of pneumoconiosis) of coal workers' pneumoconiosis (CWP) from digital chest radiography (DR) . Methods: A total of 1225 DR images of coal workers who were examined at an Occupational Disease Prevention and Control Institute in Anhui Province from October 2018 to March 2021 were retrospectively collected. All DR images were collectively diagnosed by 3 radiologists with diagnostic qualifications and gave diagnostic results. There were 692 DR images with small opacity profusion 0/- or 0/0 and 533 DR images with small opacity profusion 0/1 to stage Ⅲ of pneumoconiosis. The original chest radiographs were preprocessed differently to generate four datasets, namely 16-bit grayscale original image set (Origin16), 8-bit grayscale original image set (Origin 8), 16-bit grayscale histogram equalized image set (HE16) and 8-bit grayscale histogram equalized image set (HE8). The light-weighted CNN, ShuffleNet, was applied to train the generated prediction model on the four datasets separately. The performance of the four models for pneumoconiosis prediction was evaluated on a test set containing 130 DR images using measures such as the receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, and Youden index. The Kappa consistency test was used to compare the agreement between the model predictions and the physician diagnosed pneumoconiosis results. Results: Origin16 model achieved the highest ROC area under the curve (AUC=0.958), accuracy (92.3%), specificity (92.9%), and Youden index (0.8452) for predicting pneumoconiosis, with a sensitivity of 91.7%. And the highest consistency between identification and physician diagnosis was observed for Origin16 model (Kappa value was 0.845, 95%CI: 0.753-0.937, P<0.001). HE16 model had the highest sensitivity (98.3%) . Conclusion: The light-weighted CNN ShuffleNet model can efficiently identify the early stages of CWP, and its application in the early screening of CWP can effectively improve physicians' work efficiency.目的： 构建并验证轻量级卷积神经网络模型，探讨其在筛查煤工尘肺早期阶段（小阴影密集度达到0/1级与尘肺壹期）中的应用价值。 方法： 收集2018年10月至2021年3月在安徽省某职业病防治院进行职业健康检查的煤矿工人（共1 225例）数字化X射线胸片进行研究。所有胸片经过3名具有诊断资质的影像医生集体诊断并给出诊断结果。其中，圆形及不规则小阴影密集度为0/-或0/0级的胸片692例，0/1级至尘肺叁期的胸片533例。对原始胸片进行不同的预处理生成4个数据集，即16位灰度原始图像集（Origin16）、8位灰度原始图像集（Origin 8）、16位灰度直方图均衡图像集（HE16）和8位灰度直方图均衡图像集（HE8）。应用轻量级卷积神经网络ShuffleNet对4个数据集分别训练生成预测模型，使用受试者工作特征（ROC）曲线、准确率、灵敏度、特异度以及约登指数等指标在包含130例胸片的测试集上对4个模型的尘肺预测性能进行评估。采用Kappa一致性检验对模型预测结果与医生诊断尘肺结果进行一致性比较。 结果： Origin16模型预测尘肺获得了最高的ROC曲线下面积（AUC=0.958）、准确率（92.3%）、特异度（92.9%）和约登指数（0.845 2），灵敏度为91.7%；Origin16模型的预测结果与医生诊断结果的一致性最高（Kappa值为0.845，95%CI：0.753~0.937，P<0.001）。HE16模型的灵敏度最高（98.3%）。 结论： 轻量级卷积神经网络ShuffleNet模型可以高效地识别煤工尘肺的早期阶段，将其应用于煤工尘肺的早期筛查中可以有效地提高医生的工作效率。.