Background:Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for noninvasive myocardial tissue characterization but requires intravenous contrast agent administration. It is highly desired to develop a contrast agent–free technology to replace LGE for faster and cheaper CMR scans.Methods:A CMR virtual native enhancement (VNE) imaging technology was developed using artificial intelligence. The deep learning model for generating VNE uses multiple streams of convolutional neural networks to exploit and enhance the existing signals in native T1 maps (pixel-wise maps of tissue T1 relaxation times) and cine imaging of cardiac structure and function, presenting them as LGE-equivalent images. The VNE generator was trained using generative adversarial networks. This technology was first developed on CMR datasets from the multicenter Hypertrophic Cardiomyopathy Registry, using hypertrophic cardiomyopathy as an exemplar. The datasets were randomized into 2 independent groups for deep learning training and testing. The test data of VNE and LGE were scored and contoured by experienced human operators to assess image quality, visuospatial agreement, and myocardial lesion burden quantification. Image quality was compared using a nonparametric Wilcoxon test. Intra- and interobserver agreement was analyzed using intraclass correlation coefficients (ICC). Lesion quantification by VNE and LGE were compared using linear regression and ICC.Results:A total of 1348 hypertrophic cardiomyopathy patients provided 4093 triplets of matched T1 maps, cines, and LGE datasets. After randomization and data quality control, 2695 datasets were used for VNE method development and 345 were used for independent testing. VNE had significantly better image quality than LGE, as assessed by 4 operators (n=345 datasets; P<0.001 [Wilcoxon test]). VNE revealed lesions characteristic of hypertrophic cardiomyopathy in high visuospatial agreement with LGE. In 121 patients (n=326 datasets), VNE correlated with LGE in detecting and quantifying both hyperintensity myocardial lesions (r=0.77–0.79; ICC=0.77–0.87; P<0.001) and intermediate-intensity lesions (r=0.70–0.76; ICC=0.82–0.85; P<0.001). The native CMR images (cine plus T1 map) required for VNE can be acquired within 15 minutes and producing a VNE image takes less than 1 second.Conclusions:VNE is a new CMR technology that resembles conventional LGE but without the need for contrast administration. VNE achieved high agreement with LGE in the distribution and quantification of lesions, with significantly better image quality.

中文翻译：

---

用人工智能虚拟原生增强代替晚期钆增强，用于肥厚型心肌病的无钆心血管磁共振组织表征


背景：晚期钆增强 (LGE) 心血管磁共振 (CMR) 成像是无创心肌组织表征的金标准，但需要静脉注射造影剂。非常需要开发一种无需造影剂的技术来取代 LGE，以实现更快、更便宜的 CMR 扫描。方法：利用人工智能开发了 CMR 虚拟原生增强 (VNE) 成像技术。用于生成 VNE 的深度学习模型使用多个卷积神经网络流来利用和增强本机 T1 图中（组织 T1 弛豫时间的像素级图）和心脏结构和功能的电影成像中的现有信号，将其呈现为 LGE-等效图像。 VNE 生成器使用生成对抗网络进行训练。该技术首先是在多中心肥厚型心肌病登记处的 CMR 数据集上开发的，以肥厚型心肌病为例。数据集被随机分为 2 个独立组，用于深度学习训练和测试。 VNE 和 LGE 的测试数据由经验丰富的操作员进行评分和轮廓绘制，以评估图像质量、视觉空间一致性和心肌病变负荷量化。使用非参数 Wilcoxon 检验比较图像质量。使用组内相关系数（ICC）分析观察者内和观察者间的一致性。使用线性回归和 ICC 比较 VNE 和 LGE 的病变量化结果：总共 1348 名肥厚型心肌病患者提供了 4093 个匹配的 T1 图、电影和 LGE 数据集的三联体。经过随机化和数据质量控制后，2695 个数据集用于 VNE 方法开发，345 个数据集用于独立测试。 由 4 名操作员评估，VNE 的图像质量明显优于 LGE（n=345 个数据集； P <0 id=15>r =0.77–0.79；ICC=0.77–0.87； P <0 id=17>r =0.70– 0.76；ICC=0.82-0.85； P <0.001）。 VNE 所需的原生 CMR 图像（电影加 T1 图）可在 15 分钟内获取，生成 VNE 图像只需不到 1 秒。 结论：VNE 是一种新的 CMR 技术，类似于传统的 LGE，但不需要造影剂管理。 VNE 在病灶分布和量化方面与 LGE 达到了高度一致，图像质量明显更好。