Department of Radiology, Renmin Hospital of Wuhan University, No. 238 Jiefang Road, Wuchang District, Wuhan, 430060, China.
MR Research, GE Healthcare, Beijing, China.
BMC Med Imaging. 2024 May 31;24(1):127. doi: 10.1186/s12880-024-01308-2.
The presence of infarction in patients with unrecognized myocardial infarction (UMI) is a critical feature in predicting adverse cardiac events. This study aimed to compare the detection rate of UMI using conventional and deep learning reconstruction (DLR)-based late gadolinium enhancement (LGE and LGE, respectively) and evaluate optimal quantification parameters to enhance diagnosis and management of suspected patients with UMI.
This prospective study included 98 patients (68 men; mean age: 55.8 ± 8.1 years) with suspected UMI treated at our hospital from April 2022 to August 2023. LGE and LGE images were obtained using conventional and commercially available inline DLR algorithms. The myocardial signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and percentage of enhanced area (P) employing the signal threshold versus reference mean (STRM) approach, which correlates the signal intensity (SI) within areas of interest with the average SI of normal regions, were analyzed. Analysis was performed using the standard deviation (SD) threshold approach (2SD-5SD) and full width at half maximum (FWHM) method. The diagnostic efficacies based on LGE and LGE images were calculated.
The SNR and CNR were two times better than the SNR and CNR, respectively (P < 0.05). P was elevated compared to P using the threshold methods (P < 0.05); however, no intergroup difference was found based on the FWHM method (P > 0.05). The P and P also differed except between the 2SD and 3SD and the 4SD/5SD and FWHM methods (P < 0.05). The receiver operating characteristic curve analysis revealed that each SD method exhibited good diagnostic efficacy for detecting UMI, with the P having the best diagnostic efficacy based on the 5SD method (P < 0.05). Overall, the LGE images had better image quality. Strong diagnostic efficacy for UMI identification was achieved when the STRM was ≥ 4SD and ≥ 3SD for the LGE and LGE, respectively.
STRM selection for LGE magnetic resonance images helps improve clinical decision-making in patients with UMI. This study underscored the importance of STRM selection for analyzing LGE images to enhance diagnostic accuracy and clinical decision-making for patients with UMI, further providing better cardiovascular care.
在未识别的心肌梗死（UMI）患者中存在梗死是预测不良心脏事件的关键特征。本研究旨在比较常规和基于深度学习重建（DLR）的晚期钆增强（LGE 和 LGE）检测 UMI 的检出率，并评估最佳定量参数以增强疑似 UMI 患者的诊断和管理。
这项前瞻性研究纳入了 2022 年 4 月至 2023 年 8 月在我院接受治疗的 98 例疑似 UMI 患者（68 例男性；平均年龄：55.8±8.1 岁）。使用常规和商业可用的在线 DLR 算法获得 LGE 和 LGE 图像。使用基于信号阈值与参考平均值（STRM）的信号强度（SI）比值方法分析心肌信噪比（SNR）、对比噪声比（CNR）和增强面积百分比（P），该方法将感兴趣区域内的 SI 与正常区域的平均 SI 相关联。分析采用标准偏差（SD）阈值方法（2SD-5SD）和半峰全宽（FWHM）方法。计算基于 LGE 和 LGE 图像的诊断效能。
与常规方法相比，SNR 和 CNR 分别提高了两倍（P<0.05）。与基于阈值的方法相比，P 升高（P<0.05）；然而，基于 FWHM 方法，组间无差异（P>0.05）。除 2SD 和 3SD 与 4SD/5SD 和 FWHM 方法之间的 P 和 P 外，其他方法之间也存在差异（P<0.05）。ROC 曲线分析显示，每个 SD 方法均对检测 UMI 具有良好的诊断效能，其中 P 基于 5SD 方法具有最佳的诊断效能（P<0.05）。总体而言，LGE 图像的质量更好。当 LGE 和 LGE 的 STRM 分别≥4SD 和≥3SD 时，对 UMI 的识别具有较强的诊断效能。
选择 STRM 有助于改善 UMI 患者的临床决策。本研究强调了选择 STRM 分析 LGE 图像以提高 UMI 患者诊断准确性和临床决策的重要性，从而为 UMI 患者提供更好的心血管护理。
