A comprehensible machine learning tool to differentially diagnose idiopathic pulmonary fibrosis from other chronic interstitial lung diseases
A comprehensible machine learning tool to differentially diagnose idiopathic pulmonary fibrosis from other chronic interstitial lung diseases
复制标题
DOI：
10.1111/resp.14310
复制
发表时间：
2022-06-13
期刊：
影响因子：
6.9
通讯作者：
Hasegawa, Yoshinori
中科院分区：
文献类型：
--
作者：
Furukawa, Taiki;Oyama, Shintaro;Hasegawa, Yoshinori
背景与目的特发性肺纤维化(IPF)预后差，多学科诊断符合率低。此外，外科肺活组织检查有合并疾病的风险。因此，利用通常用于评估间质性肺疾病(ILDS)的非侵入性测试的数据，我们的目标是开发一种结合深度学习和机器学习的自动化算法，能够检测IPF并将其与其他间质性肺疾病区分开来。方法我们回顾分析了2007年4月至2017年7月期间连续出现ILD的患者。基于相应的标记图像，采用深度学习方法对HRCT图像进行语义分割。然后使用语义结果和非侵入性发现来训练诊断算法。诊断准确性采用五重交叉验证进行评估。结果1068例ILD患者共获得64.68万幅HRCT图像及相应的标记图像，其中42.7%的患者存在IPF。平均分割准确率为96.1%。机器学习算法的平均诊断准确率为83.6%，具有较高的敏感性、特异性和kappa系数值(分别为80.7%、85.8%和0.665)。使用COX风险分析，使用该算法诊断的IPF是一个重要的预后因素(风险比，2.593；95%可信区间，2.069-3.250；p<；0.001)。即使在HRCT上常见的间质性肺炎类型和手术肺活检的患者中，诊断的准确性也很好。结论利用无创性检查数据，深度学习和机器学习相结合的算法能够准确、简便、快速地诊断不同ILDS人群的IPF。
Background and objective Idiopathic pulmonary fibrosis (IPF) has poor prognosis, and the multidisciplinary diagnostic agreement is low. Moreover, surgical lung biopsies pose comorbidity risks. Therefore, using data from non-invasive tests usually employed to assess interstitial lung diseases (ILDs), we aimed to develop an automated algorithm combining deep learning and machine learning that would be capable of detecting and differentiating IPF from other ILDs. Methods We retrospectively analysed consecutive patients presenting with ILD between April 2007 and July 2017. Deep learning was used for semantic image segmentation of HRCT based on the corresponding labelled images. A diagnostic algorithm was then trained using the semantic results and non-invasive findings. Diagnostic accuracy was assessed using five-fold cross-validation. Results In total, 646,800 HRCT images and the corresponding labelled images were acquired from 1068 patients with ILD, of whom 42.7% had IPF. The average segmentation accuracy was 96.1%. The machine learning algorithm had an average diagnostic accuracy of 83.6%, with high sensitivity, specificity and kappa coefficient values (80.7%, 85.8% and 0.665, respectively). Using Cox hazard analysis, IPF diagnosed using this algorithm was a significant prognostic factor (hazard ratio, 2.593; 95% CI, 2.069-3.250; p < 0.001). Diagnostic accuracy was good even in patients with usual interstitial pneumonia patterns on HRCT and those with surgical lung biopsies. Conclusion Using data from non-invasive examinations, the combined deep learning and machine learning algorithm accurately, easily and quickly diagnosed IPF in a population with various ILDs.