利用DICOM元数据分类器自动选择腹部MRI序列并选择性使用基于像素的分类器
研究提出联合DICOM元数据分类器与基于像素分类器(对置信度低于70%的预测选择性使用)识别腹部MRI序列。元数据分类器单独使用(Group metadata)与联合方法(Group combined)在测试集总体准确率分别为0.870(95%CI 0.824–0.912)和0.930(95%CI 0.893–0.963)。联合方法对所有平扫序列分类准确率达95%以上,并改善部分增强后序列性能。
要点
- 联合元数据与像素分类器(对置信度<70%的预测选择性使用)总体准确率0.930(95%CI 0.893–0.963)。
- 元数据分类器单独使用总体准确率0.870(95%CI 0.824–0.912)。
- 联合方法对所有平扫MRI序列分类准确率≥95%。
核心结论
- 联合DICOM元数据分类器与选择性像素分类器可准确识别腹部MRI序列,测试集总体准确率0.930(95%CI 0.893–0.963)。
研究设计与样本
- 采用DICOM元数据分类器单独评估(Group metadata)及联合选择性像素分类器(对置信度低于70%的预测使用,Group combined)识别腹部MRI序列,在测试数据集上计算总体准确率及95%CI。
诊断标准与关键数值
- Group metadata测试集总体准确率0.870(95%CI 0.824–0.912)。
- Group combined测试集总体准确率0.930(95%CI 0.893–0.963)。
- 联合方法对所有平扫MRI序列分类准确率≥95%,并改善部分增强后序列性能。
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
Accurate, automated MRI series identification is important for many applications, including display ("hanging") protocols, machine learning, and radiomics. The use of the series description or a pixel-based classifier each has limitations. We demonstrate a combined approach utilizing a DICOM metadata-based classifier and selective use of a pixel-based classifier to identify abdominal MRI series. The metadata classifier was assessed alone as Group metadata and combined with selective use of the pixel-based classifier for predictions with less than 70% certainty (Group combined). The overall accuracy (mean and 95% confidence intervals) for Groups metadata and combined on the test dataset were 0.870 CI (0.824,0.912) and 0.930 CI (0.893,0.963), respectively. With this combined metadata and pixel-based approach, we demonstrate accurate classification of 95% or greater for all pre-contrast MRI series and improved performance for some post-contrast series.
引用
- Miller CM, Zhu Z, Mazurowski MA, et al. Automated selection of abdominal MRI series using a DICOM metadata classifier and selective use of a pixel-based classifier. Abdom Radiol (NY). 2024. PMID: 38860997. doi:10.1007/s00261-024-04379-5
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。