文献速递胸部CT

新型深度神经网络能否较已建立的机器学习计算机辅助检测系统改善实性肺结节的检出率并降低假阳性率

Can a Novel Deep Neural Network Improve the Computer-Aided Detection of Solid Pulmonary Nodules and the Rate of False-Positive Findings in Comparison to an Established Machine Learning Computer-Aided Detection?
PubMed 文献 · Invest Radiol · 2021-01-01

本研究回顾性纳入967例患者共2451个实性肺结节,比较基于传统机器学习的CAD系统VD10F与基于深度3D卷积神经网络的CAD系统VD20A。VD20A与VD10F敏感度相似(89.4% vs 90.7%),但特异度显著更高(62.8% vs 37.7%),每扫描假阳性率更低(0.3 vs 0.6)。

要点

  • VD20A敏感度89.4%与VD10F的90.7%相似,特异度62.8%显著高于VD10F的37.7%。
  • VD20A每扫描假阳性0.3,低于VD10F的0.6。
  • VD20A阳性预测值0.80、阴性预测值0.77,均高于VD10F的0.71和0.70。

核心结论

  • 基于深度学习的CAD软件VD20A与常规CAD软件VD10F敏感度相似,但特异度显著更高。

研究设计与样本

  • 回顾性研究,纳入967例患者共2451个实性肺结节,全部行0.6 mm薄层胸部CT(100 kV、100 mAs、高分辨率核I50f),以一位对CAD结果不知情的高年资放射科医师阅片结果为参考标准。

诊断标准与关键数值

  • VD10F检出真阳性1401个、假阴性143个、假阳性565个、真阴性342个,敏感度90.7%、特异度37.7%、阳性预测值0.71、阴性预测值0.70,每扫描假阳性0.6。
  • VD20A检出真阳性1381个、假阴性163个、假阳性337个、真阴性570个,敏感度89.4%、特异度62.8%、阳性预测值0.80、阴性预测值0.77,每扫描假阳性0.3。

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

OBJECTIVE: The aim of this study was to compare the performance of 2 approved computer-aided detection (CAD) systems for detection of pulmonary solid nodules (PSNs) in an oncologic cohort. The first CAD system is based on a conventional machine learning approach (VD10F), and the other is based on a deep 3D convolutional neural network (CNN) CAD software (VD20A).

METHODS AND MATERIALS: Nine hundred sixty-seven patients with a total of 2451 PSNs were retrospectively evaluated using the 2 different CAD systems. All patients had thin-slice chest computed tomography (0.6 mm) using 100 kV and 100 mAs and a high-resolution kernel (I50f). The CAD images generated by VD10F were transferred to the PACS for evaluation. The images generated by VD20A were evaluated using a Web browser-based viewer. Finally, a senior radiologist who was blinded for the CAD results examined the thin-slice images of every patient (ground truth).

RESULTS: A total of 2451 PSNs were detected by the senior radiologist. CAD-VD10F detected 1401 true-positive, 143 false-negative, 565 false-positive (FP), and 342 true-negative PSNs, resulting in sensitivity of 90.7%, specificity of 37.7%, positive predictive value of 0.71, and negative predictive value of 0.70. CAD-VD20A detected 1381 true-positive, 163 false-negative, 337 FP, and 570 true-negative PSNs, resulting in sensitivity of 89.4%, specificity of 62.8%, positive predictive value of 0.80, and negative predictive value 0.77, respectively. The rate of FP per scan was 0.6 for CAD-VD10F and 0.3 for CAD-VD20A.

CONCLUSIONS: The new deep learning-based CAD software (VD20A) shows similar sensitivity with the conventional CAD software (VD10F), but a significantly higher specificity.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Perl RM, Grimmer R, Hepp T, et al. Can a Novel Deep Neural Network Improve the Computer-Aided Detection of Solid Pulmonary Nodules and the Rate of False-Positive Findings in Comparison to an Established Machine Learning Computer-Aided Detection? Invest Radiol. 2021. PMID: 32796198. doi:10.1097/RLI.0000000000000713

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。