Center for Tuberculosis Control of Guangdong Province, Guangzhou, Guangdong, China.
Scientific and Technological Project Manager, Beijing Capital Technological Project Management Co., Ltd, Beijing, China.
J Xray Sci Technol. 2022;30(2):221-230. doi: 10.3233/XST-211019.
Although computer-aided detection (CAD) software employed with Artificial Intelligence (AI) system has been developed aiming to assist tuberculosis (TB) triage, screening, and diagnosis, its clinical performance for tuberculosis screening remains unknown.
To evaluate performance of an CAD software for detecting TB on chest X-ray images at a pilot active TB screening project.
A CAD software scheme employed with AI was used to screen chest X-ray images of participants and produce probability scores of cases being positive for TB. CAD-generated TB detection scores were compared with on-site and senior radiologists via several performance evaluation indices including area under the ROC curves (AUC), specificity, sensitive, and positive predict value. Pycharm CE and SPSS statistics software packages were used for data analysis.
Among 2,543 participants, eight TB patients were identified from this screening pilot program. The AI-based CAD system outperformed the onsite (AUC = 0.740) and senior radiologists (AUC = 0.805) either using thresholds of 30% (AUC = 0.978) and 50% (AUC = 0.859) when taking the final diagnosis as the ground truth.
The AI-based CAD software successfully detects all TB patients as identified from this study at a threshold of 30%. It demonstrates feasibility and easy accessibility to carry out large scale TB screening using this CAD software equipped in medical vans with chest X-ray imaging machine.
尽管已经开发出了计算机辅助检测（CAD）软件与人工智能（AI）系统结合，旨在辅助结核病（TB）分诊、筛查和诊断，但该软件在结核病筛查方面的临床性能仍不清楚。
在一项结核病主动筛查项目中评估 CAD 软件在胸部 X 光图像上检测结核病的性能。
使用一种基于 AI 的 CAD 软件方案来筛选参与者的胸部 X 光图像，并生成病例患结核病的概率得分。通过几个性能评估指标，包括 ROC 曲线下的面积（AUC）、特异性、敏感性和阳性预测值，将 CAD 生成的 TB 检测得分与现场和高级放射科医生进行比较。Pycharm CE 和 SPSS 统计软件包用于数据分析。
在 2543 名参与者中，从该筛查试点项目中发现了 8 名结核病患者。基于 AI 的 CAD 系统在使用阈值为 30%（AUC=0.978）和 50%（AUC=0.859）时，分别优于现场（AUC=0.740）和高级放射科医生（AUC=0.805），以最终诊断作为金标准。
基于 AI 的 CAD 软件成功地在阈值为 30%时检测到了该研究中所有的结核病患者。这证明了使用配备有胸部 X 光成像机的医疗车的这种 CAD 软件进行大规模结核病筛查是可行且易于实现的。
