School of Medicine, Jianghan University, Wuhan, Hubei 430056, China.
Department of Radiology, Wuhan Brain Hospital, Wuhan, Hubei 430023, China.
J Stroke Cerebrovasc Dis. 2024 Nov;33(11):107979. doi: 10.1016/j.jstrokecerebrovasdis.2024.107979. Epub 2024 Aug 31.
Early prediction of hematoma expansion (HE) is important for the development of therapeutic strategies for spontaneous intracerebral hemorrhage (sICH). Radiomics can help to predict early hematoma expansion in intracerebral hemorrhage. However, complex image processing procedures, especially hematoma segmentation, are time-consuming and dependent on assessor experience. We provide a fully automated hematoma segmentation method, and construct a hybrid predictive model for risk stratification of hematoma expansion.
To propose an automatic approach for predicting early hemorrhage expansion after spontaneous intracerebral hemorrhage using deep-learning and radiomics methods.
A total of 258 patients with sICH were retrospectively enrolled for model construction and internal validation, while another two cohorts (n=87, 149) were employed for independent validation. For hemorrhage segmentation, an iterative segmentation procedure was performed to delineate the area using an nnU-Net framework. Radiomics models of intra-hemorrhage and multiscale peri-hemorrhage were established and evaluated, and the best discriminative-scale peri-hemorrhage radiomics model was selected for further analysis. Combining clinical factors and intra- and peri-hemorrhage radiomics signatures, a hybrid nomogram was constructed for the early HE prediction using multivariate logistic regression. For model validation, the receiver operating characteristic (ROC) curve analyses and DeLong test were used to evaluate the performances of the constructed models, and the calibration curve and decision curve analysis were performed for clinical application.
Our iterative auto-segmentation model showed satisfactory results for hematoma segmentation in all four cohorts. The Dice similarity coefficient of this hematoma segmentation model reached 0.90, showing an expert-level accuracy in hematoma segmentation. The consumed time of the efficient delineation was significantly decreased, from 18 min to less than 2 min, with the assistance of the auto-segmentation model. The radiomics model of 2-mm peri-hemorrhage had a preferable area under ROC curve (AUC) of 0.840 (95 % confidence interval [CI]: 0.768, 0.912) compared with the original (0-mm dilatation) model with an AUC of 0.796 (95 % CI: 0.717, 0.875). The clinical-radiomics hybrid model showed better performances for HE prediction, with AUC of 0.853, 0.852, 0.772, and 0.818 in the training, internal validation, and independent validation cohorts 1 and 2, respectively.
The fully automatic clinical-radiomics model based on deep learning and radiomics exhibits a good ability for hematoma segmentation and a favorable performance in stratifying HE risks.
早期预测血肿扩大（HE）对于自发性脑出血（sICH）治疗策略的发展非常重要。放射组学可以帮助预测脑出血的早期血肿扩大。然而，复杂的图像处理过程，尤其是血肿分割，既耗时又依赖于评估者的经验。我们提供了一种全自动的血肿分割方法，并构建了一种混合预测模型，用于血肿扩大的风险分层。
提出一种使用深度学习和放射组学方法预测自发性脑出血后早期出血扩大的自动方法。
共回顾性纳入 258 例 sICH 患者进行模型构建和内部验证，另两个队列（n=87、149）用于独立验证。对于血肿分割，采用迭代分割程序使用 nnU-Net 框架勾勒出区域。建立并评估了颅内和多尺度脑周血肿的放射组学模型，并选择了最佳的鉴别性脑周放射组学模型进行进一步分析。结合临床因素和颅内及脑周血肿的放射组学特征，采用多元逻辑回归构建了用于早期 HE 预测的混合列线图。为了验证模型，使用受试者工作特征（ROC）曲线分析和 DeLong 检验来评估所构建模型的性能，并进行校准曲线和决策曲线分析以进行临床应用。
我们的迭代自动分割模型在所有四个队列中均显示出血肿分割的令人满意的结果。该血肿分割模型的 Dice 相似系数达到 0.90，表现出专家级的血肿分割准确性。在自动分割模型的辅助下，有效勾画的时间从 18 分钟显著减少到不到 2 分钟。与原始（0 毫米扩张）模型相比，2 毫米脑周的放射组学模型的 ROC 曲线下面积（AUC）为 0.840（95%置信区间[CI]：0.768，0.912）具有更好的效果，而原始模型的 AUC 为 0.796（95%CI：0.717，0.875）。临床放射组学混合模型在预测 HE 方面表现出更好的性能，在训练、内部验证和独立验证队列 1 和 2 中的 AUC 分别为 0.853、0.852、0.772 和 0.818。
基于深度学习和放射组学的全自动临床放射组学模型具有良好的血肿分割能力，对分层 HE 风险具有良好的性能。
