Frøysa Vidar, Berg Gøran J, Singsaas Erlend, Eftestøl Trygve, Woie Leik, Ørn Stein
Department of Cardiology, Stavanger University Hospital, Armauer Hansens vei 20, 4011 Stavanger, Norway.
Department of Electrical and Computer Science, University of Stavanger, 4036 Stavanger, P.O. box 8600, Norway.
Int J Cardiol. 2025 May 15;427:133107. doi: 10.1016/j.ijcard.2025.133107. Epub 2025 Mar 2.
Late Gadolinium-enhancement in cardiac magnetic resonance imaging (LGE-CMR) is the gold standard for assessing myocardial infarction (MI) size. Texture-based probability mapping (TPM) is a novel machine learning-based analysis of LGE images of myocardial injury. The ability of TPM to assess acute myocardial injury has not been determined.
This proof-of-concept study aimed to determine how TPM responds to the dynamic changes in myocardial injury during one-year follow-up after a first-time revascularized acute MI.
41 patients with first-time acute ST-elevation MI and single-vessel occlusion underwent successful PCI. LGE-CMR images were obtained 2 days, 1 week, 2 months, and 1 year following MI. TPM size was compared with manual LGE-CMR based MI size, LV remodeling, and biomarkers.
TPM size remained larger than MI by LGE-CMR at all time points, decreasing from 2 days to 2 months (p < 0.001) but increasing from 2 months to 1 year (p < 0.01). TPM correlated strongly with peak Troponin T (p < 0.001) and NT-proBNP (p < 0.001). At 1 week, 2 months, and 1 year, TPM showed a stronger correlation with NT-proBNP than MI size by LGE-CMR. Analyzing all collected pixels from 2 months to 1 year revealed a general increase in pixel scar probability in both the infarcted and non-infarcted regions.
This proof-of-concept study suggests that TPM may offer additional insights into myocardial alterations in both infarcted and non-infarcted regions following acute MI. These findings indicate a potential role for TPM in assessing the overall myocardial response to infarction and the subsequent healing and remodeling process.
心脏磁共振成像中的延迟钆增强（LGE-CMR）是评估心肌梗死（MI）面积的金标准。基于纹理的概率映射（TPM）是一种基于机器学习的对心肌损伤LGE图像的分析方法。TPM评估急性心肌损伤的能力尚未确定。
这项概念验证研究旨在确定TPM如何响应首次血运重建的急性心肌梗死后一年随访期间心肌损伤的动态变化。
41例首次急性ST段抬高型心肌梗死且单支血管闭塞的患者成功接受了经皮冠状动脉介入治疗（PCI）。在心肌梗死后2天、1周、2个月和1年获取LGE-CMR图像。将TPM面积与基于LGE-CMR的心肌梗死面积、左心室重构和生物标志物进行比较。
在所有时间点，TPM面积均大于LGE-CMR测量的心肌梗死面积，从2天到2个月减小（p<0.001），但从2个月到1年增加（p<0.01）。TPM与肌钙蛋白T峰值（p<0.001）和N末端脑钠肽前体（NT-proBNP，p<0.001）密切相关。在1周、2个月和1年时，TPM与NT-proBNP的相关性比LGE-CMR测量的心肌梗死面积更强。分析从2个月到1年收集的所有像素发现，梗死区和非梗死区的像素瘢痕概率总体上均增加。
这项概念验证研究表明，TPM可能为急性心肌梗死后梗死区和非梗死区的心肌改变提供更多见解。这些发现表明TPM在评估心肌对梗死的整体反应以及随后的愈合和重构过程中具有潜在作用。
