深度学习算法用于肺活检后气胸监测:一项多中心诊断队列研究
本研究回顾性纳入三个中心连续1757例经皮肺活检患者的活检后胸部X线片,评估商用深度学习算法检测气胸的性能,并与实际放射科报告及四名放射科医师的判读比较。气胸发生率17.5%(308/1757),其中16.6%(51/308)需导管引流。算法识别气胸的AUROC为0.937,敏感度70.5%、特异度97.7%;较放射科报告敏感度更高(70.2% vs. 55.5%,p < 0.001)、特异度更低(97.7% vs. 99.8%,p < 0.001)。作者认为该算法可能有助于临床实践中活检后气胸的准确及时诊断。
要点
- 活检后胸部X线片气胸发生率为17.5%(308/1757),其中16.6%(51/308)需导管引流。
- 算法识别气胸的AUROC为0.937、敏感度70.5%、特异度97.7%。
- 算法较放射科报告敏感度更高(70.2% vs. 55.5%,p < 0.001)、特异度更低(97.7% vs. 99.8%,p < 0.001)。
核心结论
- 深度学习算法在连续诊断队列的活检后胸部X线片中能适当识别气胸。
- 该算法可能有助于临床实践中活检后气胸的准确及时诊断。
研究设计与样本
- 回顾性纳入三个中心连续1757例经皮肺活检患者(1055例男性、702例女性;平均年龄65.1岁)的活检后胸部X线片。
- 使用商用深度学习算法分析每张胸部X线片以识别气胸。
- 将算法性能与实际临床实践中的放射科报告比较,并进行阅读者研究比较算法与四名放射科医师的性能。
- 以胸部放射科医师定义的参考标准,通过AUROC、敏感度和特异度评估算法与放射科医师的性能。
诊断标准与关键数值
- 算法识别气胸的AUROC为0.937、敏感度70.5%、特异度97.7%。
- 算法与放射科报告比较:敏感度70.2% vs. 55.5%(p < 0.001),特异度97.7% vs. 99.8%(p < 0.001)。
- 阅读者研究中算法与放射科医师比较:敏感度77.3% vs. 81.8-97.7%,特异度97.6% vs. 81.7-96.0%。
临床应用与阅片要点
- 原文结论指出该算法可能作为监测工具,用于活检后气胸的准确及时诊断。
局限性
- 原文未报告局限性。
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)。
英文原文(摘要)· 点击展开
OBJECTIVES: Pneumothorax is the most common and potentially life-threatening complication arising from percutaneous lung biopsy. We evaluated the performance of a deep learning algorithm for detection of post-biopsy pneumothorax in chest radiographs (CRs), in consecutive cohorts reflecting actual clinical situation.
METHODS: We retrospectively included post-biopsy CRs of 1757 consecutive patients (1055 men, 702 women; mean age of 65.1 years) undergoing percutaneous lung biopsies from three institutions. A commercially available deep learning algorithm analyzed each CR to identify pneumothorax. We compared the performance of the algorithm with that of radiology reports made in the actual clinical practice. We also conducted a reader study, in which the performance of the algorithm was compared with those of four radiologists. Performances of the algorithm and radiologists were evaluated by area under receiver operating characteristic curves (AUROCs), sensitivity, and specificity, with reference standards defined by thoracic radiologists.
RESULTS: Pneumothorax occurred in 17.5% (308/1757) of cases, out of which 16.6% (51/308) required catheter drainage. The AUROC, sensitivity, and specificity of the algorithm were 0.937, 70.5%, and 97.7%, respectively, for identification of pneumothorax. The algorithm exhibited higher sensitivity (70.2% vs. 55.5%, p < 0.001) and lower specificity (97.7% vs. 99.8%, p < 0.001), compared with those of radiology reports. In the reader study, the algorithm exhibited lower sensitivity (77.3% vs. 81.8-97.7%) and higher specificity (97.6% vs. 81.7-96.0%) than the radiologists.
CONCLUSION: The deep learning algorithm appropriately identified pneumothorax in post-biopsy CRs in consecutive diagnostic cohorts. It may assist in accurate and timely diagnosis of post-biopsy pneumothorax in clinical practice.
KEY POINTS: • A deep learning algorithm can identify chest radiographs with post-biopsy pneumothorax in multicenter consecutive cohorts reflecting actual clinical situation. • The deep learning algorithm has a potential role as a surveillance tool for accurate and timely diagnosis of post-biopsy pneumothorax.
引用
- Hwang EJ, Hong JH, Lee KH, et al. Deep learning algorithm for surveillance of pneumothorax after lung biopsy: a multicenter diagnostic cohort study. Eur Radiol. 2020. PMID: 32162001. doi:10.1007/s00330-020-06771-3
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。