Department of Imaging, The First People's Hospital of Lianyungang, Lianyungang City, China.
Department of Radiology, Hilla University College, Babylon, Iraq.
J Xray Sci Technol. 2024;32(3):735-749. doi: 10.3233/XST-230307.
This study assessed the myocardial infarction (MI) using a novel fusion approach (multi-flavored or tensor-based) of multi-parametric cardiac magnetic resonance imaging (CMRI) at four sequences; T1-weighted (T1W) in the axial plane, sense-balanced turbo field echo (sBTFE) in the axial plane, late gadolinium enhancement of heart short axis (LGE-SA) in the sagittal plane, and four-chamber views of LGE (LGE-4CH) in the axial plane.
After considering the inclusion and exclusion criteria, 115 patients (83 with MI diagnosis and 32 as healthy control patients), were included in the present study. Radiomic features were extracted from the whole left ventricular myocardium (LVM). Feature selection methods were Least Absolute Shrinkage and Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-Square (Chi2), Analysis of Variance (Anova), Recursive Feature Elimination (RFE), and SelectPersentile. The classification methods were Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF). Different metrics, including receiver operating characteristic curve (AUC), accuracy, F1- score, precision, sensitivity, and specificity were calculated for radiomic features extracted from CMR images using stratified five-fold cross-validation.
For the MI detection, Lasso (as the feature selection) and RF/LR (as the classifiers) in sBTFE sequences had the best performance (AUC: 0.97). All features and classifiers of T1 + sBTFE sequences with the weighted method (as the fused image), had a good performance (AUC: 0.97). In addition, the results of the evaluated metrics, especially mean AUC and accuracy for all models, determined that the T1 + sBTFE-weighted fused method had strong predictive performance (AUC: 0.93±0.05; accuracy: 0.93±0.04), followed by T1 + sBTFE-PCA fused method (AUC: 0.85±0.06; accuracy: 0.84±0.06).
Our selected CMRI sequences demonstrated that radiomics analysis enables to detection of MI accurately. Among the investigated sequences, the T1 + sBTFE-weighted fused method with the highest AUC and accuracy values was chosen as the best technique for MI detection.
本研究使用一种新的融合方法（多风味或张量基）对多参数心脏磁共振成像（CMRI）在四个序列中的心肌梗死（MI）进行评估：轴位 T1 加权（T1W）、轴位感平衡涡轮场回波（sBTFE）、矢状位短轴晚期钆增强（LGE-SA）和轴位四腔视图 LGE（LGE-4CH）。
在考虑纳入和排除标准后，纳入了 115 名患者（83 名 MI 诊断患者和 32 名健康对照组患者）进行本研究。从整个左心室心肌（LVM）中提取放射组学特征。特征选择方法包括最小绝对收缩和选择算子（Lasso）、最小冗余最大相关性（MRMR）、卡方（Chi2）、方差分析（Anova）、递归特征消除（RFE）和 SelectPersentile。分类方法为支持向量机（SVM）、逻辑回归（LR）和随机森林（RF）。使用分层五折交叉验证计算从 CMRI 图像中提取的放射组学特征的不同指标，包括接收者操作特征曲线（AUC）、准确性、F1 评分、精度、敏感性和特异性。
对于 MI 检测，sBTFE 序列中的 Lasso（作为特征选择）和 RF/LR（作为分类器）表现最佳（AUC：0.97）。使用加权方法（作为融合图像）的 T1+sBTFE 序列的所有特征和分类器均具有良好的性能（AUC：0.97）。此外，所有模型的评估指标结果，尤其是平均 AUC 和准确性，表明 T1+sBTFE 加权融合方法具有较强的预测性能（AUC：0.93±0.05；准确性：0.93±0.04），其次是 T1+sBTFE-PCA 融合方法（AUC：0.85±0.06；准确性：0.84±0.06）。
我们选择的 CMRI 序列表明放射组学分析能够准确检测 MI。在所研究的序列中，选择 AUC 和准确性值最高的 T1+sBTFE 加权融合方法作为 MI 检测的最佳技术。
