Righetti Francesca, Rubiu Giulia, Penso Marco, Moccia Sara, Carerj Maria L, Pepi Mauro, Pontone Gianluca, Caiani Enrico G
Department of Electronics, Information and Biomedical Engineering, Politecnico di Milano, P.zza L. da Vinci 32, 20133, Milan, Italy.
Centro Cardiologico Monzino IRCCS, Milan, Italy.
Med Biol Eng Comput. 2025 Jan;63(1):59-73. doi: 10.1007/s11517-024-03175-z. Epub 2024 Aug 6.
This work proposes a convolutional neural network (CNN) that utilizes different combinations of parametric images computed from cine cardiac magnetic resonance (CMR) images, to classify each slice for possible myocardial scar tissue presence. The CNN performance comparison in respect to expert interpretation of CMR with late gadolinium enhancement (LGE) images, used as ground truth (GT), was conducted on 206 patients (158 scar, 48 control) from Centro Cardiologico Monzino (Milan, Italy) at both slice- and patient-levels. Left ventricle dynamic features were extracted in non-enhanced cine images using parametric images based on both Fourier and monogenic signal analyses. The CNN, fed with cine images and Fourier-based parametric images, achieved an area under the ROC curve of 0.86 (accuracy 0.79, F1 0.81, sensitivity 0.9, specificity 0.65, and negative (NPV) and positive (PPV) predictive values 0.83 and 0.77, respectively), for individual slice classification. Remarkably, it exhibited 1.0 prediction accuracy (F1 0.98, sensitivity 1.0, specificity 0.9, NPV 1.0, and PPV 0.97) in patient classification as a control or pathologic. The proposed approach represents a first step towards scar detection in contrast-free CMR images. Patient-level results suggest its preliminary potential as a screening tool to guide decisions regarding LGE-CMR prescription, particularly in cases where indication is uncertain.
这项工作提出了一种卷积神经网络（CNN），该网络利用从心脏磁共振电影（CMR）图像计算出的参数图像的不同组合，对每个切片进行分类，以确定是否存在心肌瘢痕组织。在意大利米兰蒙齐诺心脏病中心的206名患者（158名瘢痕患者，48名对照患者）中，在切片和患者层面上，将该CNN的性能与用作金标准（GT）的延迟钆增强（LGE）图像的CMR专家解读进行了比较。基于傅里叶和单基因信号分析，使用参数图像在非增强电影图像中提取左心室动态特征。对于单个切片分类，输入电影图像和基于傅里叶的参数图像的CNN在ROC曲线下的面积为0.86（准确率0.79，F1值0.81，灵敏度0.9，特异性0.65，阴性预测值（NPV）和阳性预测值（PPV）分别为0.83和0.77）。值得注意的是，在将患者分类为对照或病理状态时，它表现出1.0的预测准确率（F1值0.98，灵敏度1.0，特异性0.9，NPV 1.0，PPV 0.97）。所提出的方法代表了在无对比剂CMR图像中进行瘢痕检测的第一步。患者层面的结果表明其作为一种筛查工具的初步潜力，可用于指导有关LGE-CMR处方的决策，特别是在指征不确定的情况下。
