声速 (SoS) 是一种新兴的超声造影模式，其中使用传统换能器的脉冲回波技术具有多种优势。为了估计组织 SoS 分布，根据不同波束形成序列之间的相对散斑位移进行空间域重建是一种有前途的方法。该操作基于正向模型，该模型将所寻求的 SoS 局部值与观察到的散斑偏移相关联，并解决了相关的图像重建逆问题。因此，重建精度很大程度上取决于手工制作的前向成像模型。在这项工作中，我们建议学习基于数据的 SoS 成像模型。我们引入了脉冲回波 SoS 成像问题的卷积公式，使得整个视场需要一个统一的内核，其学习变得易于处理且鲁棒。我们提出了这种卷积核的最小二乘估计，可以进一步对其进行约束和正则化以获得数值稳定性。在实验中，我们表明，与传统的手工制作的基于线的波路径模型相比，从 k 波模拟中学习的前向模型将 SoS 重建的对比度误差降低了 38%。这种模拟学习模型成功地推广到了采集的模型数据，与传统的手工制作的替代方案相比，减少了对比度误差。我们成功地证明了学习机器特定内核以及从单个图像进行一次性学习的可行性。在癌性乳腺肿瘤的体内数据上，体模学习模型表现出 34.6 m/s 的 SoS 对比度，与仅 3.4 m/s 的传统模型对比度相比有了令人印象深刻的改进。

Speed-of-sound (SoS) is an emerging ultrasound contrast modality, where pulse-echo techniques using conventional transducers offer multiple benefits. For estimating tissue SoS distributions, spatial domain reconstruction from relative speckle shifts between different beamforming sequences is a promising approach. This operates based on a forward model that relates the sought local values of SoS to observed speckle shifts, for which the associated image reconstruction inverse problem is solved. The reconstruction accuracy thus highly depends on the hand-crafted forward imaging model. In this work, we propose to learn the SoS imaging model based on data. We introduce a convolutional formulation of the pulse-echo SoS imaging problem such that the entire field-of-view requires a single unified kernel, the learning of which is then tractable and robust. We present least-squares estimation of such convolutional kernel, which can further be constrained and regularized for numerical stability. In experiments, we show that a forward model learned from k-Wave simulations reduces the contrast error of SoS reconstructions by 38%, compared to a conventional hand-crafted line-based wave-path model. This simulation-learned model generalizes successfully to acquired phantom data, reducing the contrast error compared to the conventional hand-crafted alternative. We successfully demonstrate the feasibility of learning machine-specific kernels as well as one-shot learning from a single image. On in-vivo data of a cancerous breast tumor, the phantom-learned model exhibits an SoS contrast of 34.6 m/s, as an impressive improvement over the conventional model contrast of merely 3.4 m/s.