In this paper, we propose an approach for cardiac magnetic resonance imaging (MRI), which aims to reconstruct a real-time video of a beating heart from continuous highly under-sampled measurements. This task is challenging since the object to be reconstructed (the heart) is continuously changing during signal acquisition. To address this challenge, we represent the beating heart with an implicit neural network and fit the network so that the representation of the heart is consistent with the measurements. The network in the form of a multi-layer perceptron with Fourier-feature inputs acts as an effective signal prior and enables adjusting the regularization strength in both the spatial and temporal dimensions of the signal. We examine the proposed approach for 2D free-breathing cardiac real-time MRI in different operating regimes, i.e., for different image resolutions, slice thicknesses, and acquisition lengths. Our method achieves reconstruction quality on par with or slightly better than state-of-the-art untrained convolutional neural networks and superior image quality compared to a recent method that fits an implicit representation directly to Fourier-domain measurements. However, this comes at a higher computational cost. Our approach does not require any additional patient data or biosensors including electrocardiography, making it potentially applicable in a wide range of clinical scenarios.

翻译：本文提出一种心脏磁共振成像方法，旨在从连续高度欠采样测量中重建心跳实时视频。由于待重建对象（心脏）在信号采集过程中持续变化，该任务具有挑战性。为应对这一挑战，我们采用隐式神经网络表征跳动的心脏，通过对网络进行拟合使心脏表征与测量数据保持一致。该网络采用具有傅里叶特征输入的多层感知机形式，可作为有效信号先验，并能在信号的空间和时间维度分别调整正则化强度。我们针对二维自由呼吸心脏实时MRI在不同运行场景（包括不同图像分辨率、层厚及采集时长）下验证所提方法。实验表明，本方法的重建质量可与最先进的无训练卷积神经网络相当或略优，且相比近期直接对傅里叶域测量值进行隐式表征拟合的方法具有更优图像质量，但计算成本更高。该方法无需任何额外患者数据或生物传感器（包括心电图），有望广泛应用于多种临床场景。