应对对比剂识别挑战:一种全自动机器学习方法用于预测CT成像中的对比剂期相
本回顾性研究利用1200例内部CT和240例多中心外部CT,采用开源分割算法TotalSegmentator提取解剖标志区域,训练机器学习分类器以分类静脉对比剂期相(平扫、肺动脉期、动脉期、静脉期、尿路期)并识别胃肠道对比剂。内部测试集各期AUC达99.13%–99.8%,外部验证平均AUC为97.33%和97.38%(两位标注者),胃肠道对比剂识别AUC内部为99.90%、外部为99.73%和99.31%。
要点
- 基于TotalSegmentator分割解剖标志的机器学习流程可高精度分类CT静脉对比剂期相。
- 内部测试集各期AUC均高于99%,外部多中心验证平均AUC约97.3%–97.4%。
- 该流程还能识别胃肠道对比剂,内部AUC 99.90%,外部AUC 99.73%和99.31%。
核心结论
- 整合开源分割网络与分类器可利用解剖标志有效分类对比剂期相并识别胃肠道对比剂增强。
研究设计与样本
- 回顾性研究,内部使用2016年1月4日至2022年9月12日期间采集的1200例CT扫描,外部验证使用来自多中心的240例CT扫描(The Cancer Imaging Archive);采用开源分割算法TotalSegmentator识别感兴趣区域,机器学习分类器以5折交叉验证训练,分类静脉对比剂期相(平扫、肺动脉期、动脉期、静脉期、尿路期)和胃肠道对比剂增强;性能用受试者工作特征曲线下面积(AUC)及95%置信区间评估。
诊断标准与关键数值
- 内部测试集静脉期相分类AUC:平扫期99.59% [95% CI, 99.58-99.63],肺动脉期99.50% [95% CI, 99.49-99.52],动脉期99.13% [95% CI, 99.10-99.15],静脉期99.8% [95% CI, 99.79-99.81],尿路期99.7% [95% CI, 99.68-99.7]。
- 外部数据集所有对比剂期相平均AUC:第一标注者97.33% [95% CI, 97.27-97.35],第二标注者97.38% [95% CI, 97.34-97.41]。
- 胃肠道对比剂识别AUC:内部数据集99.90% [95% CI, 99.89-99.9],外部数据集第一标注者99.73% [95% CI, 99.71-99.73],第二标注者99.31% [95% CI, 99.27-99.33]。
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
OBJECTIVES: Accurately acquiring and assigning different contrast-enhanced phases in computed tomography (CT) is relevant for clinicians and for artificial intelligence orchestration to select the most appropriate series for analysis. However, this information is commonly extracted from the CT metadata, which is often wrong. This study aimed at developing an automatic pipeline for classifying intravenous (IV) contrast phases and additionally for identifying contrast media in the gastrointestinal tract (GIT).
MATERIALS AND METHODS: This retrospective study used 1200 CT scans collected at the investigating institution between January 4, 2016 and September 12, 2022, and 240 CT scans from multiple centers from The Cancer Imaging Archive for external validation. The open-source segmentation algorithm TotalSegmentator was used to identify regions of interest (pulmonary artery, aorta, stomach, portal/splenic vein, liver, portal vein/hepatic veins, inferior vena cava, duodenum, small bowel, colon, left/right kidney, urinary bladder), and machine learning classifiers were trained with 5-fold cross-validation to classify IV contrast phases (noncontrast, pulmonary arterial, arterial, venous, and urographic) and GIT contrast enhancement. The performance of the ensembles was evaluated using the receiver operating characteristic area under the curve (AUC) and 95% confidence intervals (CIs).
RESULTS: For the IV phase classification task, the following AUC scores were obtained for the internal test set: 99.59% [95% CI, 99.58-99.63] for the noncontrast phase, 99.50% [95% CI, 99.49-99.52] for the pulmonary-arterial phase, 99.13% [95% CI, 99.10-99.15] for the arterial phase, 99.8% [95% CI, 99.79-99.81] for the venous phase, and 99.7% [95% CI, 99.68-99.7] for the urographic phase. For the external dataset, a mean AUC of 97.33% [95% CI, 97.27-97.35] and 97.38% [95% CI, 97.34-97.41] was achieved for all contrast phases for the first and second annotators, respectively. Contrast media in the GIT could be identified with an AUC of 99.90% [95% CI, 99.89-99.9] in the internal dataset, whereas in the external dataset, an AUC of 99.73% [95% CI, 99.71-99.73] and 99.31% [95% CI, 99.27-99.33] was achieved with the first and second annotator, respectively.
CONCLUSIONS: The integration of open-source segmentation networks and classifiers effectively classified contrast phases and identified GIT contrast enhancement using anatomical landmarks.
引用
- Baldini G, Hosch R, Schmidt CS, et al. Addressing the Contrast Media Recognition Challenge: A Fully Automated Machine Learning Approach for Predicting Contrast Phases in CT Imaging. Invest Radiol. 2024. PMID: 38436405. doi:10.1097/RLI.0000000000001071
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。