文献速递胸部CT

深度学习在CT图像上对小(≤2 cm)肺结节分类中的应用:初步研究

Deep Learning for the Classification of Small (≤2 cm) Pulmonary Nodules on CT Imaging: A Preliminary Study.
PubMed 文献 · Acad Radiol · 2019-11-25

本研究提出一种用于非增强胸部CT上小(≤2 cm)肺结节恶性预测的简化深度学习模型CT-lungNET,在208个结节(94个恶性、11个良性)上初步评估,其AUROC为0.85(95%CI 0.74-0.93),单层处理速度约0.90秒,快于AlexNET的8.79秒。观察者性能测试中,非放射科医生借助CT-lungNET后分类性能平均AUC提高0.13(范围0.03-0.19),放射科医生组平均AUC提高0.02(范围-0.02至0.07)。

要点

  • CT-lungNET对≤2 cm肺结节恶性分类的AUROC为0.85(95%CI 0.74-0.93),单层处理时间0.90秒。
  • 非放射科医生借助CT-lungNET后平均AUC提高0.13(范围0.03-0.19),放射科医生组提高0.02(范围-0.02至0.07)。
  • 作者认为CT-lungNET可能作为经验较少阅片者的第二阅片者,以提升早期肺癌诊断性能。
英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: We aimed to present a deep learning-based malignancy prediction model (CT-lungNET) that is simpler and faster to use in the diagnosis of small (≤2 cm) pulmonary nodules on nonenhanced chest CT and to preliminarily evaluate its performance and usefulness for human reviewers.

MATERIALS AND METHODS: A total of 173 whole nonenhanced chest CT images containing 208 pulmonary nodules (94 malignant and 11 benign nodules) ranging in size from 5 mm to 20 mm were collected. Pathologically confirmed nodules or nodules that remained unchanged for more than 1 year were included, and 30 benign and 30 malignant nodules were randomly assigned into the test set. We designed CT-lungNET to include three convolutional layers followed by two fully-connected layers and compared its diagnostic performance and processing time with those of AlexNET by using the area under the receiver operating curve (AUROC). An observer performance test was conducted involving eight human reviewers of four different groups (medical students, physicians, radiologic residents, and thoracic radiologists) at test 1 and test 2, referring to the CT-lungNET's malignancy prediction rate with pairwise comparison receiver operating curve analysis.

RESULTS: CT-lungNET showed an improved AUROC (0.85; 95% confidence interval: 0.74-0.93), compared to that of the AlexNET (0.82; 95% confidence interval: 0.71-0.91). The processing speed per one image slice for CT-lungNET was about 10 times faster than that for AlexNET (0.90 vs. 8.79 seconds). During the observer performance test, the classification performance of nonradiologists was increased with the aid of CTlungNET, (mean AUC improvement: 0.13; range: 0.03-0.19) but not significantly so in the radiologists group (mean AUC improvement: 0.02; range: -0.02 to 0.07).

CONCLUSION: CT-lungNET was able to provide better classification results with a significantly shorter amount of processing time as compared to AlexNET in the diagnosis of small pulmonary nodules on nonenhanced chest CT. In this preliminary observer performance test, CT-lungNET may have a role acting as a second reviewer for less experienced reviewers, resulting in enhanced performance in the diagnosis of early lung cancer.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Chae KJ, Jin GY, Ko SB, et al. Deep Learning for the Classification of Small (≤2 cm) Pulmonary Nodules on CT Imaging: A Preliminary Study. Acad Radiol. 2019. PMID: 31780395. doi:10.1016/j.acra.2019.05.018

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。