心脏MRI深度学习梗死定量与心肌标志物的关联
测试集800例显示AI定量与峰值CK、cTnT的相关性高于手动测量,两者对左心室不良重构的预测价值相当。
要点
- AI梗死定量与峰值CK及cTnT的相关性高于手动分割,可作为可靠的替代定量方法。
- AI测得梗死体积中位数大于手动测量(26.5 mL vs 20.1 mL),报告时需注意方法学差异。
- AI与手动测量对左心室不良重构的预测价值相当,可用于预后评估。
核心结论
- 基于心脏MRI的AI梗死定量方法与手动测量相当,并与心肌标志物强相关。
研究设计与样本
- 卷积神经网络在468例心脏MRI检查上训练,以手动梗死分割作为参考标准。
- 测试集包含800例患者,中位年龄58岁(IQR 51-67岁),83%为男性。
关键影像表现/征象
- CNN估测的中位梗死体积大于手动测量(26.5 mL vs 20.1 mL;P < .001)。
诊断标准与关键数值
- AI测量与峰值CK的相关性为r = 0.76、ρ = 0.80,高于手动分割的r = 0.68、ρ = 0.72(P < .001)。
- AI测量与峰值cTnT的相关性为r = 0.66,手动分割为r = 0.57(P = .004)。
- 手动与AI测量对左心室不良重构的预测价值相当(P = .24)。
临床应用与阅片要点
- AI梗死定量可直接用于心脏MRI延迟强化图像的梗死体积测量,相关性与标志物更高。
- 阅片时注意AI与手动测量的梗死体积存在系统性差异,AI数值偏大。
- AI定量可用于左心室不良重构风险评估,预测效能与手动测量一致。
局限性
- 研究为回顾性设计,可能存在选择偏倚。
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
Purpose To evaluate the reliability and clinical applicability of an artificial intelligence (AI)-based infarct size quantification method based on cardiac MR images in patients with ST-elevation myocardial infarction (STEMI). Materials and Methods This retrospective study included patients with acute STEMI who underwent cardiac MRI between January 2005 and October 2024. A convolutional neural network (CNN) was trained on 468 unique cardiac MRI examinations, with manual infarct segmentations serving as the reference standard. On a test set, correlations between manual and AI-determined infarct sizes and peak creatine kinase (CK) and cardiac troponin T (cTnT) levels were assessed using Pearson and Spearman correlation analyses. The predictive value of the manual and AI-based measurements for the occurrence of left ventricular adverse remodeling (LVAR) was compared using the DeLong test. Results The test set comprised 800 patients (median age, 58 years [IQR, 51-67 years]; 83% male). The CNN estimated a larger median infarct size than the manual measurements did (26.5 vs 20.1 mL; P < .001). The correlation with peak CK levels was greater (P < .001) for the automated measurements (r = 0.76, ρ = 0.80) than for manual segmentations (r = 0.68, ρ = 0.72). The same relationship was observed for peak cTnT levels (r = 0.66 vs r = 0.57; P = .004). Manual and AI-based measurements demonstrated comparable predictive value for LVAR (P = .24). Conclusion The AI-based infarct size quantification method based on cardiac MRI is comparable to manual measurement and is strongly correlated with cardiac biomarkers. Keywords: MR-Imaging, Cardiac, Heart, Ischemia/Infarction, Segmentation, Late Gadolinium Enhancement, ST Elevation Myocardial Infarction, Convolutional Neural Networks, Cardiac Biomarkers Supplemental material is available for this article. © The Author(s) 2026. Published by the Radiological Society of North America under a CC BY 4.0 license. ClinicalTrials.gov identifier: NCT04113356.
引用
- Schwab, Pamminger, Kremser, et al. Association of Deep Learning-based Myocardial Infarction Size Quantification in Cardiac MRI with Cardiac Biomarker Levels. Radiol Cardiothorac Imaging. 2026. PMID: 42347575. doi:10.1148/ryct.250235
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。