The First College for Clinical Medicine, Shanxi Medical University, No. 56 Xinjian South Road, Taiyuan, 030001, Shanxi, People's Republic of China.
Network Security Department, Shanxi Police College, No. 799 Qingdong Road, Qingxu Country, Taiyuan, 030021, Shanxi, People's Republic of China.
BMC Pulm Med. 2022 Jul 15;22(1):271. doi: 10.1186/s12890-022-02068-x.
This paper aims to develop a successful deep learning model with data augmentation technique to discover the clinical uniqueness of chest X-ray imaging features of coal workers' pneumoconiosis (CWP).
We enrolled 149 CWP patients and 68 dust-exposure workers for a prospective cohort observational study between August 2021 and December 2021 at First Hospital of Shanxi Medical University. Two hundred seventeen chest X-ray images were collected for this study, obtaining reliable diagnostic results through the radiologists' team, and confirming clinical imaging features. We segmented regions of interest with diagnosis reports, then classified them into three categories. To identify these clinical features, we developed a deep learning model (ShuffleNet V2-ECA Net) with data augmentation through performances of different deep learning models by assessment with Receiver Operation Characteristics (ROC) curve and area under the curve (AUC), accuracy (ACC), and Loss curves.
We selected the ShuffleNet V2-ECA Net as the optimal model. The average AUC of this model was 0.98, and all classifications of clinical imaging features had an AUC above 0.95.
We performed a study on a small dataset to classify the chest X-ray clinical imaging features of pneumoconiosis using a deep learning technique. A deep learning model of ShuffleNet V2 and ECA-Net was successfully constructed using data augmentation, which achieved an average accuracy of 98%. This method uncovered the uniqueness of the chest X-ray imaging features of CWP, thus supplying additional reference material for clinical application.
本研究旨在开发一种成功的深度学习模型，并结合数据增强技术，以发现煤工尘肺（CWP）胸部 X 射线影像学特征的临床独特性。
我们纳入了 149 例 CWP 患者和 68 名尘暴露工人，进行了一项前瞻性队列观察研究，时间为 2021 年 8 月至 2021 年 12 月，地点为山西医科大学第一医院。本研究共采集了 217 张胸部 X 射线图像，通过放射科医生团队获得可靠的诊断结果，并确认了临床影像学特征。我们使用诊断报告对感兴趣区域进行分割，然后将其分为三类。为了识别这些临床特征，我们开发了一个深度学习模型（ShuffleNet V2-ECA Net），通过评估不同深度学习模型的性能，结合数据增强技术，包括接收者操作特征（ROC）曲线和曲线下面积（AUC）、准确性（ACC）和损失曲线。
我们选择了 ShuffleNet V2-ECA Net 作为最优模型。该模型的平均 AUC 为 0.98，所有临床影像学特征的分类 AUC 均高于 0.95。
我们使用深度学习技术对小数据集进行了研究，以分类尘肺病的胸部 X 射线临床影像学特征。通过数据增强成功构建了 ShuffleNet V2 和 ECA-Net 的深度学习模型，平均准确率为 98%。该方法揭示了 CWP 胸部 X 射线影像学特征的独特性，为临床应用提供了更多参考依据。
