自动机器学习与放射科医师在CT评估子宫内膜中的表现比较
本研究基于926例患者的常规CT图像,提取影像组学特征联合年龄构建机器学习模型,区分子宫内膜癌与正常子宫内膜。自动机器学习(TPOT)在外部队列测试集上AUC达0.79,准确度和特异度均高于放射科医师平均水平,敏感度与医师相仿。
要点
- TPOT模型在外部测试集准确度0.80、特异度0.90,均高于放射科医师平均的0.49和0.51。
- TPOT与放射科医师的敏感度分别为0.61和0.46,差异无统计学意义。
- 常规CT上基于影像组学特征联合年龄可辅助区分子宫内膜癌与正常子宫内膜。
核心结论
- 自动机器学习能够在常规CT图像上区分子宫内膜癌与正常子宫内膜,准确度和特异度高于放射科医师。
研究设计与样本
- 单中心(原文未报告多中心)研究,共纳入926例患者,其中子宫内膜癌416例、正常子宫内膜510例。
- 手动分割CT图像,以子宫内膜或子宫为感兴趣区提取非纹理与纹理特征,并将临床特征「年龄」纳入特征集。
- 数据划分为训练集、验证集、测试集及外部测试集,比较人工优化管线与TPOT导出的最佳管线在测试集和外部测试集上的表现,并与放射科医师比较。
诊断标准与关键数值
- 人工优化管线(reliefF特征选择+Bagging分类器)在外部测试集上AUC 0.73,准确度0.73(95%CI 0.62-0.82),敏感度0.64(95%CI 0.45-0.79),特异度0.78(95%CI 0.65-0.87)。
- TPOT管线在外部测试集上AUC 0.79,准确度0.80(95%CI 0.70-0.87),敏感度0.61(95%CI 0.43-0.77),特异度0.90(95%CI 0.78-0.96)。
- TPOT与放射科医师平均表现比较:准确度0.80 vs. 0.49(p < 0.001),特异度0.90 vs. 0.51(p < 0.001),敏感度0.61 vs. 0.46(p = 0.130)。
临床应用与阅片要点
- 在常规CT阅片时,可关注子宫内膜区域的影像组学特征并结合患者年龄,辅助判断子宫内膜癌可能。
- TPOT模型特异度高但敏感度有限,阴性结果不能完全排除子宫内膜癌,需结合临床及其他检查。
局限性
- 原文未明确报告研究是否为单中心或回顾性设计,但样本来源于单一机构且为回顾性图像分析,外部泛化性需进一步验证。
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
PURPOSE: In this study, we developed radiomic models that utilize a combination of imaging features and clinical variables to distinguish endometrial cancer (EC) from normal endometrium on routine computed tomography (CT).
METHODS: A total of 926 patients consisting of 416 endometrial cancer (EC) and 510 normal endometrium were included. The CT images of these patients were segmented manually, and divided into training, validation, testing and external testing sets. Non-texture and texture features of these images with endometrium or uterus as region of interest were extracted. The clinical feature "age" was also included in the feature set. Feature selection and machine learning classifier were applied to normalized feature set. This manual optimized combination was then compared with the best pipeline exported by Tree-Based Pipeline Optimization Tool (TPOT) on testing and external testing set. The performances of these machine learning pipelines were compared to that of radiologists.
RESULTS: The manual expert optimized pipeline using the "reliefF" feature selection method and "Bagging" classifier on the external testing set achieved a test ROC AUC of 0.73, accuracy of 0.73 (95% CI 0.62-0.82), sensitivity of 0.64 (95% CI 0.45-0.79), and specificity of 0.78 (95% CI 0.65-0.87), while TPOT achieved a test ROC AUC of 0.79, accuracy of 0.80 (95% CI 0.70-0.87), sensitivity of 0.61 (95% CI 0.43-0.77), and specificity of 0.90 (95% CI 0.78-0.96). When compared to average radiologist performance, the TPOT achieved higher test accuracy (0.80 vs. 0.49, p < 0.001) and specificity (0.90 vs. 0.51, p < 0.001), with comparable sensitivity (0.61 vs. 0.46, p = 0.130).
CONCLUSION: Our results demonstrate that automatic machine learning can distinguish EC from normal endometrium on routine CT imaging with higher accuracy and specificity than radiologists.
引用
- Li D, Hu R, Li H, et al. Performance of automatic machine learning versus radiologists in the evaluation of endometrium on computed tomography. Abdom Radiol (NY). 2021. PMID: 34286371. doi:10.1007/s00261-021-03210-9
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。