基于深度学习活动性肺结核胸片自动检测算法的开发与验证
DLAD分类性能为0.977-1.000,定位性能为0.973-1.000;在高敏感度和高特异度截断值下,敏感度分别为94.3%-100%和84.1%-99.0%,特异度分别为91.1%-100%和99.1%-100%。与15名医生相比,DLAD在分类和定位上均显著更优。
要点
- DLAD在活动性肺结核胸片检测中表现出色,分类和定位性能均优于包括胸部放射科医生在内的所有医生组。
- 高敏感度截断值下敏感度94.3%-100%、特异度91.1%-100%;高特异度截断值下敏感度84.1%-99.0%、特异度99.1%-100%。
- 该算法有望辅助结核病筛查流程,但需进一步临床验证。
核心结论
- DLAD在活动性肺结核胸片检测中表现出优异且一致的性能,优于包括胸部放射科医生在内的医生。
主要发现
- DLAD分类性能(ROC曲线下面积)为0.977-1.000,定位性能(替代自由响应ROC曲线下面积)为0.973-1.000。
- 高敏感度截断值下,分类敏感度94.3%-100%,特异度91.1%-100%。
- 高特异度截断值下,分类敏感度84.1%-99.0%,特异度99.1%-100%。
- DLAD分类性能(0.993)显著高于所有医生组(0.746-0.971),定位性能(0.993)也显著高于所有医生组(0.664-0.925)。
临床怎么用
- DLAD可作为活动性肺结核胸片筛查的辅助工具,帮助简化筛查流程并提高诊断性能。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Detection of active pulmonary tuberculosis on chest radiographs (CRs) is critical for the diagnosis and screening of tuberculosis. An automated system may help streamline the tuberculosis screening process and improve diagnostic performance. METHODS: We developed a deep learning-based automatic detection (DLAD) algorithm using 54c221 normal CRs and 6768 CRs with active pulmonary tuberculosis that were labeled and annotated by 13 board-certified radiologists. The performance of DLAD was validated using 6 external multicenter, multinational datasets. To compare the performances of DLAD with physicians, an observer performance test was conducted by 15 physicians including nonradiology physicians, board-certified radiologists, and thoracic radiologists. Image-wise classification and lesion-wise localization performances were measured using area under the receiver operating characteristic (ROC) curves and area under the alternative free-response ROC curves, respectively. Sensitivities and specificities of DLAD were calculated using 2 cutoffs (high sensitivity [98%] and high specificity [98%]) obtained through in-house validation. RESULTS: DLAD demonstrated classification performance of 0.977-1.000 and localization performance of 0.973-1.000. Sensitivities and specificities for classification were 94.3%-100% and 91.1%-100% using the high-sensitivity cutoff and 84.1%-99.0% and 99.1%-100% using the high-specificity cutoff. DLAD showed significantly higher performance in both classification (0.993 vs 0.746-0.971) and localization (0.993 vs 0.664-0.925) compared to all groups of physicians. CONCLUSIONS: Our DLAD demonstrated excellent and consistent performance in the detection of active pulmonary tuberculosis on CR, outperforming physicians, including thoracic radiologists.
引用
- Hwang EJ, Park S, Jin KN, et al. Development and Validation of a Deep Learning-based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs. Clin Infect Dis. 2019. PMID: 30418527. doi:10.1093/cid/ciy967
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。