人工智能辅助肺结节分割与特征提取的诊断研究
本研究基于LUNA16数据集,比较深度学习分割方法并用IBSI标准提取特征,结合PCA与三种机器学习方法构建AI诊断系统,并融合Lung-RADS。结节分割CPM达0.83,分类准确率92%,与金标准kappa系数0.68,总体诊断准确率0.75,未来将开展外部临床验证。
要点
- AI系统分割肺结节CPM为0.83,分类准确率92%,可作为Lung-RADS辅助工具。
- 与金标准kappa系数0.68,总体诊断准确率0.75,提示分类一致性中等。
- 研究基于LUNA16公开数据集,尚未在临床数据中验证。
核心结论
- AI辅助肺结节诊断流程在LUNA16数据集上表现优于既往文献,但需外部临床验证。
研究设计与样本
- 研究为方法学开发与验证,使用LUNA16公开数据集训练和测试AI系统。
- 流程包括比较深度学习分割方法、用IBSI标准提取特征并降维、PCA结合三种机器学习方法分类。
- 参考标准为LUNA16数据集提供的金标准(结节标注或分类标签)。
诊断标准与关键数值
- 结节分割的CPM评分为0.83。
- 结节分类准确率为92%,与金标准的kappa系数为0.68。
- 按结节计算的总体诊断准确率为0.75。
临床应用与阅片要点
- 该AI系统可辅助放射科医生进行肺结节分割和特征提取,提高LDCT阅片效率。
- 融合Lung-RADS的分级思路有助于规范肺结节报告,但需注意AI仅作为辅助工具。
- 实际应用中需关注AI对结节分割和分类的准确性,尤其需结合临床和影像特征综合判断。
局限性
- 研究仅基于LUNA16公开数据集,未在临床数据中验证,泛化能力未知。
- 原文未报告外部测试结果,需未来外部临床研究验证。
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
AIM: To develop a high-accuracy low-dose computed tomography (LDCT) lung nodule diagnosis system by combining artificial intelligence (AI) technology with the Lung CT Screening Reporting and Data System (Lung-RADS), which can be used in the future AI-aided diagnosis of pulmonary nodules.
MATERIALS AND METHODS: The study comprised the following steps: (1) the best deep-learning segmentation method for pulmonary nodules was compared and selected objectively; (2) the Image Biomarker Standardization Initiative (IBSI) was used for feature extraction and to determine the best feature reduction method; and (3) a principal component analysis (PCA) and three machine learning methods were used to analyse the extracted features, and the best method was determined. The Lung Nodule Analysis 16 dataset was applied to train and test the established system in this study.
RESULTS: The competition performance metric (CPM) score of the nodule segmentation reached 0.83, the accuracy of nodule classification was 92%, the kappa coefficient with the ground truth was 0.68, and the overall diagnostic accuracy (calculated by the nodules) was 0.75.
CONCLUSION: This paper summarises a more efficient AI-assisted diagnosis process of pulmonary nodules, and has better performance compared with the previous literature. In addition, this method will be validated in a future external clinical study.
引用
- Tang, Lin, Liang, et al. Artificial intelligence aided diagnosis of pulmonary nodules segmentation and feature extraction. Clin Radiol. 2023. PMID: 37028999. doi:10.1016/j.crad.2023.03.002
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。