改良三维U-Net深度学习模型在胸部CT肺结节自动检测中的开发与验证:基于肺图像数据库联盟和日本数据集
本研究开发并验证了一种改良三维U-Net深度学习模型,用于胸部CT肺结节自动检测。模型在肺图像数据库联盟和图像数据库资源计划数据集上训练,内部验证使用89例未参与训练的胸部CT,外部验证使用日本某城市大学医院的450例胸部CT。内部验证CPM为94.7%(95%CI 89.1%-98.6%),外部验证CPM为83.3%(95%CI 79.4%-86.1%)。
要点
- 改良3D U-Net模型在内部验证中CPM达94.7%,外部验证中CPM为83.3%。
- 外部验证使用日本城市大学医院450例胸部CT,每例至少含一个>5 mm结节。
- 模型性能在内外验证中均较高,但外部验证低于内部验证。
核心结论
- 改良3D U-Net深度学习模型在内部和外部验证中均表现出较高性能,内部验证CPM为94.7%(95%CI 89.1%-98.6%),外部验证CPM为83.3%(95%CI 79.4%-86.1%)。
研究设计与样本
- 回顾性研究,符合《健康保险携带和责任法案》并经机构审查委员会批准,使用肺图像数据库联盟和图像数据库资源计划数据集训练模型,内部验证采用89例未用于训练的胸部CT,外部验证采用日本某城市大学医院450例胸部CT,参考标准为经验丰富放射科医生识别的至少一个>5 mm结节。
诊断标准与关键数值
- 采用竞赛性能指标(CPM)评估模型准确性,即每扫描1/8、1/4、1/2、1、2、4、8个假阳性时的平均敏感度;95%置信区间通过1000次自助法计算。
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
RATIONALE AND OBJECTIVES: A more accurate lung nodule detection algorithm is needed. We developed a modified three-dimensional (3D) U-net deep-learning model for the automated detection of lung nodules on chest CT images. The purpose of this study was to evaluate the accuracy of the developed modified 3D U-net deep-learning model.
MATERIALS AND METHODS: In this Health Insurance Portability and Accountability Act-compliant, Institutional Review Board-approved retrospective study, the 3D U-net based deep-learning model was trained using the Lung Image Database Consortium and Image Database Resource Initiative dataset. For internal model validation, we used 89 chest CT scans that were not used for model training. For external model validation, we used 450 chest CT scans taken at an urban university hospital in Japan. Each case included at least one nodule of >5 mm identified by an experienced radiologist. We evaluated model accuracy using the competition performance metric (CPM) (average sensitivity at 1/8, 1/4, 1/2, 1, 2, 4, and 8 false-positives per scan). The 95% confidence interval (CI) was computed by bootstrapping 1000 times.
RESULTS: In the internal validation, the CPM was 94.7% (95% CI: 89.1%-98.6%). In the external validation, the CPM was 83.3% (95% CI: 79.4%-86.1%).
CONCLUSION: The modified 3D U-net deep-learning model showed high performance in both internal and external validation.
引用
- Suzuki K, Otsuka Y, Nomura Y, et al. Development and Validation of a Modified Three-Dimensional U-Net Deep-Learning Model for Automated Detection of Lung Nodules on Chest CT Images From the Lung Image Database Consortium and Japanese Datasets. Acad Radiol. 2020. PMID: 32839096. doi:10.1016/j.acra.2020.07.030
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。