Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, 210006, China.
Laboratory of Image Science and Technology, School of Computer Science and Engineering, Southeast University, Nanjing, 210096, China.
Eur Radiol. 2024 Oct;34(10):6808-6819. doi: 10.1007/s00330-024-10619-5. Epub 2024 Mar 15.
We aimed to develop machine learning (ML) models based on diffusion- and perfusion-weighted imaging fusion (DP fusion) for identifying stroke within 4.5 h, to compare them with DWI- and/or PWI-based ML models, and to construct an automatic segmentation-classification model and compare with manual labeling methods.
ML models were developed from multimodal MRI datasets of acute stroke patients within 24 h of clear symptom onset from two centers. The processes included manual segmentation, registration, DP fusion, feature extraction, and model establishment (logistic regression (LR) and support vector machine (SVM)). A segmentation-classification model (X-Net) was proposed for automatically identifying stroke within 4.5 h. The area under the receiver operating characteristic curve (AUC), sensitivity, Dice coefficients, decision curve analysis, and calibration curves were used to evaluate model performance.
A total of 418 patients (≤ 4.5 h: 214; > 4.5 h: 204) were evaluated. The DP fusion model achieved the highest AUC in identifying the onset time in the training (LR: 0.95; SVM: 0.92) and test sets (LR: 0.91; SVM: 0.90). The DP fusion-LR model displayed consistent positive and greater net benefits than other models across a broad range of risk thresholds. The calibration curve demonstrated the good calibration of the DP fusion-LR model (average absolute error: 0.049). The X-Net model obtained the highest Dice coefficients (DWI: 0.81; Tmax: 0.83) and achieved similar performance to manual labeling (AUC: 0.84).
The automatic segmentation-classification models based on DWI and PWI fusion images had high performance in identifying stroke within 4.5 h.
Perfusion-weighted imaging (PWI) fusion images had high performance in identifying stroke within 4.5 h. The automatic segmentation-classification models based on DWI and PWI fusion images could provide clinicians with decision-making guidance for acute stroke patients with unknown onset time.
• The diffusion/perfusion-weighted imaging fusion model had the best performance in identifying stroke within 4.5 h. • The X-Net model had the highest Dice and achieved performance close to manual labeling in segmenting lesions of acute stroke. • The automatic segmentation-classification model based on DP fusion images performed well in identifying stroke within 4.5 h.
我们旨在开发基于弥散加权成像（DWI）和灌注加权成像（PWI）融合（DP 融合）的机器学习（ML）模型，用于识别 4.5 小时内的中风，并与基于 DWI 和/或 PWI 的 ML 模型进行比较，构建自动分割分类模型并与手动标记方法进行比较。
从两个中心急性卒中患者 24 小时内的多模态 MRI 数据集中开发 ML 模型。该过程包括手动分割、注册、DP 融合、特征提取和模型建立（逻辑回归（LR）和支持向量机（SVM））。提出了一种分割分类模型（X-Net），用于自动识别 4.5 小时内的中风。使用受试者工作特征曲线下面积（AUC）、敏感性、Dice 系数、决策曲线分析和校准曲线来评估模型性能。
共评估了 418 例患者（≤4.5 小时：214 例；＞4.5 小时：204 例）。DP 融合模型在训练集（LR：0.95；SVM：0.92）和测试集（LR：0.91；SVM：0.90）中识别发病时间的 AUC 最高。DP 融合-LR 模型在广泛的风险阈值范围内显示出一致的正净收益，且大于其他模型。校准曲线表明 DP 融合-LR 模型具有良好的校准性能（平均绝对误差：0.049）。X-Net 模型获得了最高的 Dice 系数（DWI：0.81；Tmax：0.83），并与手动标记具有相似的性能（AUC：0.84）。
基于 DWI 和 PWI 融合图像的自动分割分类模型在识别 4.5 小时内的中风方面具有较高的性能。
灌注加权成像（PWI）融合图像在识别 4.5 小时内的中风方面具有较高的性能。基于 DWI 和 PWI 融合图像的自动分割分类模型可为发病时间未知的急性脑卒中患者提供决策指导。
DP 融合模型在识别 4.5 小时内的中风方面表现最佳。
X-Net 模型的 Dice 最高，在分割急性脑卒中病灶方面的性能接近手动标记。
基于 DP 融合图像的自动分割分类模型在识别 4.5 小时内的中风方面表现良好。
