论文标题
SPICER：自动线圈灵敏度估计和重建的MRI的自我监督学习
SPICER: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation and Reconstruction
论文作者
论文摘要
集成物理测量模型和学习的图像正规化器的深层架构（DMBA）被广泛用于并行磁共振成像（PMRI）。 PMRI的传统DMBA依赖于预估计的线圈灵敏度图（CSM）作为测量模型的组成部分。但是，当测量值高度不足时，准确CSM的估计是一个具有挑战性的问题。此外，对DMBA的传统培训需要高质量的地面图像，从而限制了它们在难以获得地面图的应用中的使用。本文通过将香料作为一种新方法来解决这些问题，该方法将自我监督的学习和自动线圈灵敏度估算估算。香料没有使用预估计的CSM，而是同时重建准确的MR图像并估算高质量的CSM。香料还可以从没有任何地面图的情况下从不足的嘈杂测量中学习。我们在实验收集的数据上验证了香料，表明它可以在高度加速的数据采集设置（最高10倍）中实现最先进的性能。
Deep model-based architectures (DMBAs) integrating physical measurement models and learned image regularizers are widely used in parallel magnetic resonance imaging (PMRI). Traditional DMBAs for PMRI rely on pre-estimated coil sensitivity maps (CSMs) as a component of the measurement model. However, estimation of accurate CSMs is a challenging problem when measurements are highly undersampled. Additionally, traditional training of DMBAs requires high-quality groundtruth images, limiting their use in applications where groundtruth is difficult to obtain. This paper addresses these issues by presenting SPICE as a new method that integrates self-supervised learning and automatic coil sensitivity estimation. Instead of using pre-estimated CSMs, SPICE simultaneously reconstructs accurate MR images and estimates high-quality CSMs. SPICE also enables learning from undersampled noisy measurements without any groundtruth. We validate SPICE on experimentally collected data, showing that it can achieve state-of-the-art performance in highly accelerated data acquisition settings (up to 10x).
