一种全局特征管理新方案提高了影像组学模型的性能与稳定性:基于急性脑干梗死CT图像的研究
本研究基于两个医学中心的急性脑干梗死非增强CT图像,提出一种不依赖降维的全局特征管理新方案,并与传统降维方案对照。新方案在检测任务上AUC与传统方案相近(0.875 vs 0.883),但在预后预测上AUC更高(0.864 vs 0.806),且检测与预测模型的稳定性均更好(ΔAUC 0.013 vs 0.039;0.004 vs 0.044)。
要点
- 新方案(Swavelet)对急性脑干梗死的检测性能与传统方案相近(AUC 0.875 vs 0.883)。
- 新方案对早期神经功能恶化的预测性能优于传统方案(AUC 0.864 vs 0.806)。
- 新方案在检测与预测模型中的稳定性均更强(ΔAUC 0.013 vs 0.039;0.004 vs 0.044)。
核心结论
- 不依赖降维的全局特征管理方案可能成为影像组学方法学的有力补充。
研究设计与样本
- 基于两个医学中心急性脑干梗死患者非增强CT图像的研究,分为测试集与验证集,比较全局特征管理新方案与传统降维方案,特征在Matlab R2013a中提取,采用广义线性模型和多变量逻辑回归评估模型性能。
诊断标准与关键数值
- 检测模型AUC:新方案0.875 vs 传统方案0.883。
- 预后预测模型AUC:新方案0.864(OR=0.917,p=0.021) vs 传统方案0.806(OR=0.972,p=0.007)。
- 稳定性以测试集与验证集间AUC差值评估:检测模型ΔAUC新方案0.013 vs 传统方案0.039;预测模型ΔAUC新方案0.004 vs 传统方案0.044。
临床应用与阅片要点
- 作者认为不依赖降维的全局特征管理方案可能成为影像组学方法学的有力补充。
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
OBJECTIVE: The performance and stability of radiomics model caused by dimension reduction remain being confronted with major challenges. In this study, we aimed to propose a new scheme of global feature management independent of dimension reduction to improve it.
METHODS: The non-contrast computed tomography (NCCT) images of acute brainstem infarction (ABI) from two medical centers were used as test and validation sets. A new scheme was constructed based on global feature management, and the traditional scheme dependent on dimension reduction was used as control. The radiomic features of NCCT images were extracted in Matlab R2013a. The performance of prediction model was evaluated by the generalized linear model (GLM) and multivariate logistic regression. And, the stability of radiomics model was evaluated with the difference of area under curve (AUC) between the test and validation sets.
RESULTS: Compared with the traditional scheme, the new scheme presented a similar detection performance (AUC: 0.875 vs. 0.883), yet a better performance in predicting prognosis (AUC: 0.864, OR = 0.917, p = 0.021 vs. AUC:0.806, OR = 0.972, p = 0.007). All these results were well verified in an independent validation set. Moreover, the new scheme showed stronger stability in both the detection model (ΔAUC: 0.013 vs. 0.039) and prediction model (ΔAUC = 0.004 vs. 0.044).
CONCLUSION: Although there might be several limitations, this study proved that the scheme of global feature management independent of dimension reduction could be a powerful supplement to the radiomics methodology.
KEY POINTS: • The new scheme (Swavelet) presented similar detection performances for ABI with the traditional scheme. • A better predictive performance for END was found in the new scheme (Swavelet) compared with the traditional scheme. • Stronger model stability was found in both the detection and prediction models based on the new scheme.
引用
- Li, Xie, Xu, et al. A new scheme of global feature management improved the performance and stability of radiomics model: a study based on CT images of acute brainstem infarction. Eur Radiol. 2022. PMID: 35267092. doi:10.1007/s00330-022-08659-w
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。