梗死区与非梗死区脑区均对基于深度学习的MRI急性卒中结局预测有贡献
该研究在449例急性缺血性卒中患者中开发并验证深度学习模型,利用卒中后1-7天MRI DWI及90天mRS数据,比较不同输入(梗死体积、全脑图像、梗死掩模等)对预测90天mRS的准确性。结果显示全脑图像输入表现最佳(MAE 1.07),仅梗死体积输入最差(MAE 1.51),提示梗死位置、信号特征及非梗死区均对预测有贡献。
要点
- 全脑图像输入预测90天mRS的MAE最低为1.07,优于仅用梗死体积的1.51。
- 非梗死区脑组织可能反映整体脑健康与储备,对结局预测有独立贡献。
- 预测不良结局(mRS>2)的AUC从梗死体积的0.68提升至全脑输入的0.86。
核心结论
- 虽然全脑成像体积输入获得最佳性能,但梗死位置、信号特征以及非梗死区均对预测有贡献,非梗死区可能反映整体脑健康与储备。
研究设计与样本
- 在449例急性缺血性卒中患者中开发并验证深度学习模型,使用卒中后1-7天MRI DWI扫描及90天mRS结局数据,训练输入包括梗死体积、全脑图像、梗死掩模、保留强度的梗死掩模及去除梗死区的病灶中和图像。
关键影像表现/征象
- 仅用梗死体积训练的模型MAE最高(最差)为1.51分(95%CI 1.40-1.61;P<.001)。
- 全脑图像训练的模型MAE最低为1.07分(95%CI 0.99-1.16)。
- 梗死掩模、保留强度的梗死掩模及病灶中和图像的MAE分别为1.25(95%CI 1.15-1.34;P=.002)、1.21(95%CI 1.11-1.30;P=.008)和1.35(95%CI 1.24-1.45;P<.001)。
诊断标准与关键数值
- 预测具体mRS评分的准确性、±1个mRS分类内的准确性、平均绝对误差(MAE)及预测不良结局(mRS>2)的AUC。
- 预测不良结局的AUC从梗死体积的0.68(95%CI 0.63-0.73)到全脑输入的0.86(95%CI 0.82-0.89)。
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
BACKGROUND AND PURPOSE: Predicting long-term clinical outcomes based on early acute ischemic stroke (AIS) information would be useful for many reasons, including patient counseling and clinical trial execution. This study investigates how different regions in brain imaging, including noninfarcted areas, contribute to the accuracy of predicting 90-day stroke outcomes by using deep learning (DL).
MATERIALS AND METHODS: We developed and validated DL models in 449 patients with AIS, by using MRI DWI scans from 1-7 days poststroke and 90-day mRS outcome data. These models were trained on various inputs: infarct volumes, full-brain images, infarct masks, intensity-preserved infarct masks, and images in which the infarct region is removed, which we call lesion-neutralized images. Performance was assessed by using accuracy of predicting the specific mRS score, accuracy within ±1 mRS category, mean absolute error (MAE), and the area under the curve (AUC) to predict unfavorable outcome (mRS > 2).
RESULTS: The model trained by using only infarct volume size reported the highest (worst) MAE of 1.51 points (95% CI, 1.40-1.61; P < .001), while the model trained with full-brain images achieved the lowest MAE of 1.07 points (95% CI, 0.99-1.16). Models with intermediate amounts of imaging information each improved on the volume-only predictions but did not reach the performance of the full brain images; infarct masks, intensity-preserved infarct masks, and lesion-neutralized images demonstrated MAEs of 1.25 (95% CI, 1.15-1.34; P = .002), 1.21 (95% CI, 1.11-1.30; P = .008), and 1.35 (95% CI, 1.24-1.45; P < .001), respectively. Similar results were seen for other prediction tasks, including AUC to predict unfavorable outcomes, ranging from 0.68 (95% CI, 0.63-0.73) for infarct volume to 0.86 (95% CI, 0.82-0.89) for full brain inputs.
CONCLUSIONS: While the best performance came from by using the full brain imaging volume, we demonstrate that the infarct location, its signal characteristics, and importantly, the noninfarcted regions all contribute to the predictions. The noninfarcted areas may be a proxy for overall brain health and resilience, containing important information about potential outcomes.
引用
- Liu Y, Jiang B, van Voorst H, et al. Both Infarcted and Noninfarcted Brain Regions Contribute to Deep Learning-Based MRI Prediction of Acute Stroke Outcome. AJNR Am J Neuroradiol. 2025. PMID: 41198223. doi:10.3174/ajnr.A8896
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。