影像组学特征分布的协调化:对CT图像中肝组织分类的影响
本研究回顾性分析76例多中心门静脉期CT序列,在脾和肝放置感兴趣体积并提取9个影像组学特征,比较基于脾的Z-score与按中心的ComBat两种协调方法前后特征分布和分类性能。结果显示肝与脾特征分布均不同(p<0.05);肝vs脾检测Z-score协调AUC=93.1%(p<0.001);病例对照设置下肝病vs非肝病两种协调无差异(平均AUC=73.6%,p=0.49);全数据集ComBat性能提升AUC=82.4%(p=0.05),Z-score降至AUC=67.4%(p=0.008)。
要点
- 肝与脾的影像组学特征分布均存在差异(p<0.05),提示基于脾的协调需先做好数据构建。
- 肝vs脾分类中Z-score协调AUC=93.1%(p<0.001)。
- 肝病vs非肝病在病例对照设置下两种协调无差异(平均AUC=73.6%,p=0.49)。
核心结论
- 数据协调需首先关注数据构建,以避免降低后续分类性能。
- 基于脾的影像组学特征协调后行肝组织分类,是改善肝病组织检测的有前景策略。
研究设计与样本
- 回顾性分析76例多中心门静脉期CT序列,包含非肝病与肝病患者。
- 在每例序列的脾和肝放置感兴趣体积,提取9个影像组学特征(直方图与纹理)。
- 评估两种协调方法:基于脾测量计算肝测量的Z-score;按各影像中心计算ComBat参数(在脾计算并应用于肝)。
- 比较协调前后的特征分布与分类性能,分类任务为非肝病vs脾及非肝病vs肝病组织。
诊断标准与关键数值
- 肝与脾的影像组学特征分布均不同(p<0.05)。
- 肝vs脾检测:Z-score协调AUC=93.1%(p<0.001)。
- 肝病vs非肝病(病例对照设置):两种协调无差异,平均AUC=73.6%(p=0.49)。
- 肝病vs非肝病(全数据集):ComBat协调AUC=82.4%(p=0.05),Z-score协调AUC=67.4%(p=0.008)。
临床应用与阅片要点
- 原文未据此给出推荐。
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: Following the craze for radiomic features (RF), their lack of reliability raised the question of the generalizability of classification models. Inter-site harmonization of images therefore becomes a central issue. We compared RF harmonization processing designed to detect liver diseases in CT images.
METHODS: We retrospectively analyzed 76 multi-center portal CT series of non-diseased (NDL) and diseased liver (DL) patients. In each series, we positioned volumes of interest in spleen and liver, then extracted 9 RF (histogram and texture). We evaluated two RF harmonization approaches. First, in each series, we computed the Z-score of liver measurements based on those computed in the spleen. Second, we evaluated the ComBat method according to each imaging center; parameters were computed in the spleen and applied to the liver. We compared RF distributions and classification performances before/after harmonization. We classified NDL versus spleen and versus DL tissues.
RESULTS: The RF distributions were all different between liver and spleen (p < 0.05). The Z-score harmonization outperformed for the detection of liver versus spleen: AUC = 93.1% (p < 0.001). For the detection of DL versus NDL, in a case/control setting, we found no differences between the harmonizations: mean AUC = 73.6% (p = 0.49). Using the whole datasets, the performances were improved using ComBat (p = 0.05) AUC = 82.4% and degraded with Z-score AUC = 67.4% (p = 0.008).
CONCLUSIONS: Data harmonization requires to first focus on data structuring to not degrade the performances of subsequent classifications. Liver tissue classification after harmonization of spleen-based RF is a promising strategy for improving the detection of DL tissue.
KEY POINTS: • Variability of acquisition parameter makes radiomics of CT features non-reproducible. • Data harmonization can help circumvent the inter-site variability of acquisition protocols. • Inter-site harmonization must be carefully implemented and requires designing consistent data sets.
引用
- Beaumont H, Iannessi A, Bertrand AS, et al. Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging. Eur Radiol. 2021. PMID: 33459855. doi:10.1007/s00330-020-07641-8
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。