Department of Radiology, Peking University First Hospital, No. 8, Xishiku Street, Xicheng District, Beijing, 100034, China.
Eur Radiol. 2020 Jan;30(1):87-98. doi: 10.1007/s00330-019-06378-3. Epub 2019 Aug 5.
To develop a radiomics model for predicting hematoma expansion in patients with intracerebral hemorrhage (ICH) and to compare its predictive performance with a conventional radiological feature-based model.
We retrospectively analyzed 251 consecutive patients with acute ICH. Two radiologists independently assessed baseline noncontrast computed tomography (NCCT) images. For each radiologist, a radiological model was constructed from radiological variables; a radiomics score model was constructed from high-dimensional quantitative features extracted from NCCT images; and a combined model was constructed using both radiological variables and radiomics score. Development of models was constructed in a primary cohort (n = 177). We then validated the results in an independent validation cohort (n = 74). The primary outcome was hematoma expansion. We compared the three models for predicting hematoma expansion. Predictive performance was assessed with the receiver operating characteristic (ROC) curve analysis.
In the primary cohort, combined model and radiomics model showed greater AUCs than radiological model for both readers (all p < .05). In the validation cohort, combined model and radiomics model showed greater AUCs, sensitivities, and accuracies than radiological model for reader 2 (all p < .05). Combined model showed greater AUC than radiomics model for reader 1 only in the primary cohort (p = .03). Performance of three models was comparable between reader 1 and reader 2 in both cohorts (all p > .05).
NCCT-based radiomics model showed high predictive performance and outperformed radiological model in the prediction of early hematoma expansion in ICH patients.
• Radiomics model showed better performance for prediction of hematoma expansion in patients with intracerebral hemorrhage than radiological feature-based model. • Hematomas which expanded in follow-up NCCT tended to be larger in baseline volume, more irregular in shape, more heterogeneous in composition, and coarser in texture. • A radiomics model provides a convenient and objective tool for prediction of hematoma expansion that helps to define subsets of patients who would benefit from anti-expansion therapy.
开发一种针对颅内出血（ICH）患者血肿扩大的放射组学模型，并与传统的基于影像学特征的模型进行比较，以评估其预测性能。
我们回顾性分析了 251 例连续的急性 ICH 患者。两位放射科医生分别对基线期非增强 CT（NCCT）图像进行评估。对于每位放射科医生，均从影像学变量构建一个放射学模型，从 NCCT 图像中提取高维定量特征构建放射组学评分模型，然后使用影像学变量和放射组学评分构建联合模型。在主要队列（n=177）中构建模型，然后在独立验证队列（n=74）中验证结果。主要结局为血肿扩大。我们比较了三种模型对血肿扩大的预测能力。通过接受者操作特征（ROC）曲线分析评估预测性能。
在主要队列中，对于两位读者，联合模型和放射组学模型的 AUC 均大于放射学模型（均 P<.05）。在验证队列中，对于读者 2，联合模型和放射组学模型的 AUC、敏感度和准确率均大于放射学模型（均 P<.05）。在主要队列中，仅读者 1 的联合模型 AUC 大于放射组学模型（P=.03）。在两个队列中，读者 1 和读者 2 之间三种模型的性能均无差异（均 P>.05）。
基于 NCCT 的放射组学模型在预测 ICH 患者早期血肿扩大方面表现出较高的预测性能，优于基于影像学特征的模型。
放射组学模型在预测颅内出血患者血肿扩大方面的表现优于基于影像学特征的模型。
随访期 NCCT 中扩大的血肿在基线期体积上较大，形状上更不规则，成分上更不均匀，质地更粗糙。
放射组学模型为预测血肿扩大提供了一种便捷和客观的工具，有助于确定需要抗扩大治疗的患者亚组。
