A prospective multicenter clinical research study validating the effectiveness and safety of a chest X-ray-based pulmonary tuberculosis screening software JF CXR-1 built on a convolutional neural network algorithm

Frontiers in Medicine

Medicine

Shuihua Lu¹  Lu Xia¹  Dailun Hou²  Fuping Yang³  Ning Liu⁴  Yuqing Wu⁵  Yang Yang⁶  Ping Liu⁶  Hongqiu Pan⁷ 

[1] Department of Pulmonary Medicine, National Clinical Research Center for Infectious Disease, Shenzhen Third People's Hospital/The Second Affiliated Hospital, School of Medicine, Southern University of Science and Technology, Shenzhen, Guangdong, China;Department of Radiology, Beijing Chest Hospital, Capital Medical University, Beijing, China;Department of Tuberculosis, Chongqing Public Health Medical Center, Southwest University, Chongqing, China;Department of Tuberculosis, Hebei Chest Hospital, Shijiangzhuang, Hebei, China;Department of Tuberculosis, Jiangxi Chest Hospital, Nanchang, Jiangxi, China;Department of Tuberculosis, Shanghai Public Health Clinical Center Affiliated to Fudan University, Shanghai, China;Department of Tuberculosis, The Third Hospital of Zhenjiang, Zhenjiang, Jiangsu, China;

关键词: tuberculosis;    screening;    radiography;    deep learning;    convolutional neural network algorithm;    computer-aided detection (CAD);    diagnosis;   

DOI  :  10.3389/fmed.2023.1195451

 received in 2023-03-28, accepted in 2023-07-24,  发布年份 2023

来源: Frontiers

【 摘 要 】

BackgroundChest radiography (chest X-ray or CXR) plays an important role in the early detection of active pulmonary tuberculosis (TB). In areas with a high TB burden that require urgent screening, there is often a shortage of radiologists available to interpret the X-ray results. Computer-aided detection (CAD) software employed with artificial intelligence (AI) systems may have the potential to solve this problem.ObjectiveWe validated the effectiveness and safety of pulmonary tuberculosis imaging screening software that is based on a convolutional neural network algorithm.MethodsWe conducted prospective multicenter clinical research to validate the performance of pulmonary tuberculosis imaging screening software (JF CXR-1). Volunteers under the age of 15 years, both with or without suspicion of pulmonary tuberculosis, were recruited for CXR photography. The software reported a probability score of TB for each participant. The results were compared with those reported by radiologists. We measured sensitivity, specificity, consistency rate, and the area under the receiver operating characteristic curves (AUC) for the diagnosis of tuberculosis. Besides, adverse events (AE) and severe adverse events (SAE) were also evaluated.ResultsThe clinical research was conducted in six general infectious disease hospitals across China. A total of 1,165 participants were enrolled, and 1,161 were enrolled in the full analysis set (FAS). Men accounted for 60.0% (697/1,161). Compared to the results from radiologists on the board, the software showed a sensitivity of 94.2% (95% CI: 92.0–95.8%) and a specificity of 91.2% (95% CI: 88.5–93.2%). The consistency rate was 92.7% (91.1–94.1%), with a Kappa value of 0.854 (P = 0.000). The AUC was 0.98. In the safety set (SS), which consisted of 1,161 participants, 0.3% (3/1,161) had AEs that were not related to the software, and no severe AEs were observed.ConclusionThe software for tuberculosis screening based on a convolutional neural network algorithm is effective and safe. It is a potential candidate for solving tuberculosis screening problems in areas lacking radiologists with a high TB burden.

【 授权许可】

Unknown   
Copyright © 2023 Yang, Xia, Liu, Yang, Wu, Pan, Hou, Liu and Lu.