Utah Center for Advanced Imaging Research (UCAIR), Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah, USA.
Department of Biomedical Engineering, University of Utah, Salt Lake City, Utah, USA.
Med Phys. 2022 Nov;49(11):6986-7000. doi: 10.1002/mp.15801. Epub 2022 Jun 21.
Using the spin-lattice relaxation time (T1) as a biomarker, the myocardium can be quantitatively characterized using cardiac T1 mapping. The modified Look-Locker inversion (MOLLI) recovery sequences have become the standard clinical method for cardiac T1 mapping. However, the MOLLI sequences require an 11-heartbeat breath-hold that can be difficult for subjects, particularly during exercise or pharmacologically induced stress. Although shorter cardiac T1 mapping sequences have been proposed, these methods suffer from reduced precision. As such, there is an unmet need for accelerated cardiac T1 mapping.
To accelerate cardiac T1 mapping MOLLI sequences by using neural networks to estimate T1 maps using a reduced number of T1-weighted images and their corresponding inversion times.
In this retrospective study, 911 pre-contrast T1 mapping datasets from 202 subjects (128 males, 56 ± 15 years; 74 females, 54 ± 17 years) and 574 T1 mapping post-contrast datasets from 193 subjects (122 males, 57 ± 15 years; 71 females, 54 ± 17 years) were acquired using the MOLLI-5(3)3 sequence and the MOLLI-4(1)3(1)2 sequence, respectively. All acquisition protocols used similar scan parameters: , , and , gadoteridol (ProHance, Bracco Diagnostics) dose . A bidirectional multilayered long short-term memory (LSTM) network with fully connected output and cyclic model-based loss was used to estimate T1 maps from the first three T1-weighted images and their corresponding inversion times for pre- and post-contrast T1 mapping. The performance of the proposed architecture was compared to the three-parameter T1 recovery model using the same reduction of the number of T1-weighted images and inversion times. Reference T1 maps were generated from the scanner using the full MOLLI sequences and the three-parameter T1 recovery model. Correlation and Bland-Altman plots were used to evaluate network performance in which each point represents averaged regions of interest in the myocardium corresponding to the standard American Heart Association 16-segment model. The precision of the network was examined using consecutively repeated scans. Stress and rest pre-contrast MOLLI studies as well as various disease test cases, including amyloidosis, hypertrophic cardiomyopathy, and sarcoidosis were also examined. Paired t-tests were used to determine statistical significance with .
Our proposed network demonstrated similar T1 estimations to the standard MOLLI sequences (pre-contrast: vs. with ; post-contrast: vs. with ). The precision of standard MOLLI sequences was well preserved with the proposed network architecture ( vs. ). Network-generated T1 reactivities are similar to stress and rest pre-contrast MOLLI studies ( vs. with ). Amyloidosis T1 maps generated using the proposed network are also similar to the reference T1 maps (pre-contrast: vs. with ; post-contrast: vs. with ).
A bidirectional multilayered LSTM network with fully connected output and cyclic model-based loss was used to generate high-quality pre- and post-contrast T1 maps using the first three T1-weighted images and their corresponding inversion times. This work demonstrates that combining deep learning with cardiac T1 mapping can potentially accelerate standard MOLLI sequences from 11 to 3 heartbeats.
使用自旋晶格弛豫时间（T1）作为生物标志物，通过心脏 T1 映射可以对心肌进行定量特征描述。改良的 Look-Locker 反转（MOLLI）恢复序列已成为心脏 T1 映射的标准临床方法。然而，MOLLI 序列需要 11 次心跳的屏气，这对于受试者来说可能很困难，尤其是在运动或药物引起的应激期间。尽管已经提出了更短的心脏 T1 映射序列，但这些方法的精度降低。因此，需要加速心脏 T1 映射。
通过使用神经网络来估计 T1 图，使用较少数量的 T1 加权图像及其相应的反转时间来加速心脏 T1 映射 MOLLI 序列。
在这项回顾性研究中，使用 MOLLI-5(3)3 序列分别从 202 名受试者（128 名男性，56 ± 15 岁；74 名女性，54 ± 17 岁）和 MOLLI-4(1)3(1)2 序列分别从 193 名受试者（122 名男性，57 ± 15 岁；71 名女性，54 ± 17 岁）获得 911 次预对比 T1 映射数据集和 574 次 T1 映射后数据集。所有采集方案均使用相似的扫描参数： ， ， ，钆特醇（普罗汉，百力司康）剂量 。使用具有全连接输出和循环模型基损失的双向多层长短期记忆（LSTM）网络来估计预对比和后对比 T1 映射的前三个 T1 加权图像及其相应的反转时间的 T1 图。与使用相同数量的 T1 加权图像和反转时间的三参数 T1 恢复模型相比，比较了所提出的架构的性能。参考 T1 图是使用全 MOLLI 序列和三参数 T1 恢复模型从扫描仪生成的。使用平均感兴趣区的相关和 Bland-Altman 图来评估网络性能，其中每个点表示对应于标准美国心脏协会 16 节段模型的心肌区域。使用连续重复扫描来检查网络的精度。还检查了应激和静息预对比 MOLLI 研究以及各种疾病测试病例，包括淀粉样变性、肥厚型心肌病和结节病。使用 进行配对 t 检验以确定统计学意义。
我们提出的网络与标准 MOLLI 序列的 T1 估计值相似（预对比： vs. 与 ；后对比： vs. 与 ）。所提出的网络架构很好地保留了标准 MOLLI 序列的精度（ vs. ）。网络生成的 T1 反应性与应激和静息预对比 MOLLI 研究相似（ vs. 与 ）。使用所提出的网络生成的淀粉样变性 T1 图也与参考 T1 图相似（预对比： vs. 与 ；后对比： vs. 与 ）。
使用具有全连接输出和循环模型基损失的双向多层 LSTM 网络，可以使用前三个 T1 加权图像及其相应的反转时间生成高质量的预对比和后对比 T1 图。这项工作表明，将深度学习与心脏 T1 映射相结合，可以潜在地将标准 MOLLI 序列从 11 次心跳加速到 3 次心跳。
