Demirel Omer Burak, Ghanbari Fahime, Hoeger Christopher W, Tsao Connie W, Carty Adele, Ngo Long H, Pierce Patrick, Johnson Scott, Arcand Kathryn, Street Jordan, Rodriguez Jennifer, Wallace Tess E, Chow Kelvin, Manning Warren J, Nezafat Reza
Department of Medicine (Cardiovascular Division) and Harvard Medical School, Boston, Massachusetts, USA.
Department of Medicine (Cardiovascular Division) and Harvard Medical School, Boston, Massachusetts, USA; Siemens Medical Solutions USA, Inc., Boston, Massachusetts, USA.
J Cardiovasc Magn Reson. 2024 Nov 28;27(1):101127. doi: 10.1016/j.jocmr.2024.101127.
Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging enables imaging of scar/fibrosis and is a cornerstone of most CMR imaging protocols. CMR imaging can benefit from image acceleration; however, image acceleration in LGE remains challenging due to its limited signal-to-noise ratio. In this study, we sought to evaluate a rapid two-dimensional (2D) LGE imaging protocol using a generative artificial intelligence (AI) algorithm with inline reconstruction.
A generative AI-based image enhancement was used to improve the sharpness of 2D LGE images acquired with low spatial resolution in the phase-encode direction. The generative AI model is an image enhancement technique built on the enhanced super-resolution generative adversarial network. The model was trained using balanced steady-state free-precession cine images, readily used for LGE without additional training. The model was implemented inline, allowing the reconstruction of images on the scanner console. We prospectively enrolled 100 patients (55 ± 14 years, 72 males) referred for clinical CMR at 3T. We collected three sets of LGE images in each subject, with in-plane spatial resolutions of 1.5 × 1.5-3-6 mm. The generative AI model enhanced in-plane resolution to 1.5 × 1.5 mm from the low-resolution counterparts. Images were compared using a blur metric, quantifying the perceived image sharpness (0 = sharpest, 1 = blurriest). LGE image sharpness (using a 5-point scale) was assessed by three independent readers.
The scan times for the three imaging sets were 15 ± 3, 9 ± 2, and 6 ± 1 s, with inline generative AI-based images reconstructed time of ∼37 ms. The generative AI-based model improved visual image sharpness, resulting in lower blur metric compared to low-resolution counterparts (AI-enhanced from 1.5 × 3 mm resolution: 0.3 ± 0.03 vs 0.35 ± 0.03, P < 0.01). Meanwhile, AI-enhanced images from 1.5 × 3 mm resolution and original LGE images showed similar blur metric (0.30 ± 0.03 vs 0.31 ± 0.03, P = 1.0) Additionally, there was an overall 18% improvement in image sharpness between AI-enhanced images from 1.5 × 3 mm resolution and original LGE images in the subjective blurriness score (P < 0.01).
The generative AI-based model enhances the image quality of 2D LGE images while reducing the scan time and preserving imaging sharpness. Further evaluation in a large cohort is needed to assess the clinical utility of AI-enhanced LGE images for scar evaluation, as this proof-of-concept study does not provide evidence of an impact on diagnosis.
延迟钆增强（LGE）心血管磁共振（CMR）成像能够对瘢痕/纤维化进行成像，是大多数CMR成像方案的基石。CMR成像可受益于图像加速；然而，由于LGE的信噪比有限，其图像加速仍然具有挑战性。在本研究中，我们试图评估一种使用具有在线重建功能的生成式人工智能（AI）算法的快速二维（2D）LGE成像方案。
基于生成式AI的图像增强技术用于提高在相位编码方向上以低空间分辨率采集的2D LGE图像的清晰度。生成式AI模型是一种基于增强超分辨率生成对抗网络构建的图像增强技术。该模型使用平衡稳态自由进动电影图像进行训练，无需额外训练即可直接用于LGE。该模型在扫描控制台在线实现，允许在其上重建图像。我们前瞻性纳入了100例因临床CMR检查而转诊至3T的患者（年龄55±14岁，男性72例）。我们在每个受试者中收集了三组LGE图像，其平面内空间分辨率为1.5×1.5 - 3 - 6 mm。生成式AI模型将平面内分辨率从低分辨率对应图像提高到1.5×1.5 mm。使用模糊度量对图像进行比较，量化感知到的图像清晰度（0 = 最清晰，1 = 最模糊）。由三位独立阅片者评估LGE图像的清晰度（采用5分制）。
三组成像的扫描时间分别为15±3秒、9±2秒和6±1秒，基于在线生成式AI的图像重建时间约为37毫秒。基于生成式AI的模型提高了视觉图像清晰度，与低分辨率对应图像相比，模糊度量更低（从1.5×3 mm分辨率进行AI增强：0.3±0.03对0.35±0.03，P < 0.01）。同时，从1.5×3 mm分辨率进行AI增强的图像与原始LGE图像显示出相似的模糊度量（0.30±0.03对0.31±0.03，P = 1.0）。此外，在主观模糊度评分中，从1.5×3 mm分辨率进行AI增强的图像与原始LGE图像相比，图像清晰度总体提高了18%（P < 0.01）。
基于生成式AI的模型在提高2D LGE图像质量的同时，减少了扫描时间并保持了成像清晰度。由于本概念验证研究未提供对诊断影响的证据，因此需要在更大队列中进行进一步评估，以评估AI增强的LGE图像在瘢痕评估中的临床应用价值。
