最近,基于得分的扩散模型在MRI重建中表现出令人满意的性能。这些方法中的大多数都需要大量完全采样的MRI数据作为培训集,有时在实践中很难获得。本文提出了用于MRI重建的完全采样的基于无DATA的分数扩散模型,该模型以不足的采样数据以自我监督的方式学习了完全采样的MR图像。具体而言,我们首先通过贝叶斯深度学习从未采样的数据中推断出完全采样的MR图像分布,然后通过训练分数函数来扰动数据分布并近似其概率密度梯度。利用学到的分数函数为先验,我们可以通过执行条件的Langevin Markov链蒙特卡洛(MCMC)采样来重建MR图像。公共数据集的实验表明,所提出的方法优于现有的自我监督的MRI重建方法,并与常规(完全采样的数据训练)基于得分的扩散方法实现可比性的性能。
translated by 谷歌翻译
最近,未经训练的神经网络(UNNS)显示了在随机采样轨迹上对MR图像重建的令人满意的性能,而无需使用其他全面采样训练数据。但是,现有的基于UNN的方法并未完全使用MR图像物理先验,导致某些常见情况(例如部分傅立叶,常规采样等)的性能差,并且缺乏重建准确性的理论保证。为了弥合这一差距,我们使用特殊设计的UNN提出了一种保障的K空间插值方法,该方法使用特殊设计的UNN,该方法由MR图像的三个物理先验(或K空间数据)驱动,包括稀疏,线圈灵敏度平稳性和相位平滑度。我们还证明,所提出的方法保证了插值K空间数据准确性的紧密界限。最后,消融实验表明,所提出的方法比现有传统方法更准确地表征了MR图像的物理先验。此外,在一系列常用的采样轨迹下,实验还表明,所提出的方法始终优于传统的平行成像方法和现有的UNN,甚至超过了最先进的监督训练的K空间深度学习方法案例。
translated by 谷歌翻译
降解扩散概率模型(DDPM)已显示在MRI重建中具有出色的性能。从连续的随机微分方程(SDE)的角度来看,DDPM的反向过程可被视为最大化重建的MR图像的能量,从而导致SDE序列发散。因此,提出了用于MRI重建的修改高频DDPM模型。从其连续的SDE观点(称为高频空间SDE)(HFS-SDE),MR图像的能量浓缩低频部分不再得到放大,并且扩散过程更多地集中在获取高频的先验信息上。它不仅提高了扩散模型的稳定性,而且还提供了更好地恢复高频细节的可能性。公开FastMRI数据集的实验表明,我们提出的HFS-SDE优于DDPM驱动的VP-SDE,有监督的深度学习方法和传统的平行成像方法,就稳定性和重建精度而言。
translated by 谷歌翻译
由低级别正则化驱动的深度学习方法在动态磁共振(MR)成像中实现了有吸引力的性能。但是,这些方法中的大多数代表了手工制作的核标准的低级别先验,该规范无法通过固定的正则化参数准确地近似整个数据集的低排名先验。在本文中,我们提出了一种学习动态MR成像的低级方法。特别是,我们将部分可分离(PS)模型的半季度分裂方法(HQS)算法传输到网络中,其中低级别以可学习的空空间变换自适应地表征。心脏CINE数据集的实验表明,所提出的模型的表现优于最新的压缩传感(CS)方法和现有的深度学习方法,既有定量和质量上的深度学习方法。
translated by 谷歌翻译
最近,模型驱动的深度学习通过用网络模块替换符号器的一阶信息(即(子)梯度或近端运算符)来拓展到级联网络中的一定迭代算法,该算法呈现出更可说明的与常见的数据驱动网络相比,可以预测。相反,理论上,不一定存在这样的功能常规程序,其一级信息与替换的网络模块匹配,这意味着网络输出可能不被原始正则化模型覆盖。此外,到目前为止,在现实假设下,也没有保证展开网络的全球收敛性和鲁棒性(规律性)。为了弥合这一差距,本文建议在展开网络上提出保障方法。具体而言,专注于加速MRI,我们展开了一个零阶算法,网络模块代表常规器本身,使得网络输出可以仍然被正则化模型覆盖。此外,受到深度均衡模型的理想的启发,在反向化之前,我们执行了展开的迭代网络,以收敛到一个固定点,以确保收敛。如果测量数据包含噪声,我们证明了所提出的网络对嘈杂干扰具有强大。最后,数值实验表明,所提出的网络始终如一地优于最先进的MRI重建方法,包括传统的正规化方法和其他深度学习方法。
translated by 谷歌翻译
目的:提出一种新的基于深度学习的方法,称为RG-NET(重建和生成网络),用于通过向下采样k空间高度加速的MR参数映射,并同时减少所获取的对比度。方法:所提出的框架包括重建模块和生成模块。在先前的帮助下,重建模块从所获取的少数下采样的k空间数据重建MR图像。然后,生成模块从重建的图像中综合剩余的多对比度图像,其中通过对完全采样标签的监督隐式模型被隐式地结合到图像生成中。在不同的加速率下对膝关节和大脑的映射数据进行评估RG-Net。 Cartilage和大脑的区域T1 \ R {HO}进行了分析,以获得RG-Net的性能。结果:RG-Net以高速加速度为17的高质量T1 \ R {Ho}地图。与仅借出k空间的竞争方法相比,我们的框架在T1 \ R {Ho}值中实现了更好的性能分析。我们的方法还提高了胶质瘤患者T1 \ R {Ho}的质量。结论:提出的RG-NET通过欠采样k空间采用新策略并同时减少快速先生参数映射的对比度,可以实现高加速率,同时保持良好的重建质量。我们的框架的生成模块也可以用作其他快速MR参数映射方法的插入模块。关键词:深度学习,卷积神经网络,快速先生参数映射
translated by 谷歌翻译
Feature transformation for AI is an essential task to boost the effectiveness and interpretability of machine learning (ML). Feature transformation aims to transform original data to identify an optimal feature space that enhances the performances of a downstream ML model. Existing studies either combines preprocessing, feature selection, and generation skills to empirically transform data, or automate feature transformation by machine intelligence, such as reinforcement learning. However, existing studies suffer from: 1) high-dimensional non-discriminative feature space; 2) inability to represent complex situational states; 3) inefficiency in integrating local and global feature information. To fill the research gap, we formulate the feature transformation task as an iterative, nested process of feature generation and selection, where feature generation is to generate and add new features based on original features, and feature selection is to remove redundant features to control the size of feature space. Finally, we present extensive experiments and case studies to illustrate 24.7\% improvements in F1 scores compared with SOTAs and robustness in high-dimensional data.
translated by 谷歌翻译
Urban traffic speed prediction aims to estimate the future traffic speed for improving the urban transportation services. Enormous efforts have been made on exploiting spatial correlations and temporal dependencies of traffic speed evolving patterns by leveraging explicit spatial relations (geographical proximity) through pre-defined geographical structures ({\it e.g.}, region grids or road networks). While achieving promising results, current traffic speed prediction methods still suffer from ignoring implicit spatial correlations (interactions), which cannot be captured by grid/graph convolutions. To tackle the challenge, we propose a generic model for enabling the current traffic speed prediction methods to preserve implicit spatial correlations. Specifically, we first develop a Dual-Transformer architecture, including a Spatial Transformer and a Temporal Transformer. The Spatial Transformer automatically learns the implicit spatial correlations across the road segments beyond the boundary of geographical structures, while the Temporal Transformer aims to capture the dynamic changing patterns of the implicit spatial correlations. Then, to further integrate both explicit and implicit spatial correlations, we propose a distillation-style learning framework, in which the existing traffic speed prediction methods are considered as the teacher model, and the proposed Dual-Transformer architectures are considered as the student model. The extensive experiments over three real-world datasets indicate significant improvements of our proposed framework over the existing methods.
translated by 谷歌翻译
We revisit a simple Learning-from-Scratch baseline for visuo-motor control that uses data augmentation and a shallow ConvNet. We find that this baseline has competitive performance with recent methods that leverage frozen visual representations trained on large-scale vision datasets.
translated by 谷歌翻译
Recently, many deep learning based beamformers have been proposed for multi-channel speech separation. Nevertheless, most of them rely on extra cues known in advance, such as speaker feature, face image or directional information. In this paper, we propose an end-to-end beamforming network for direction guided speech separation given merely the mixture signal, namely MIMO-DBnet. Specifically, we design a multi-channel input and multiple outputs architecture to predict the direction-of-arrival based embeddings and beamforming weights for each source. The precisely estimated directional embedding provides quite effective spatial discrimination guidance for the neural beamformer to offset the effect of phase wrapping, thus allowing more accurate reconstruction of two sources' speech signals. Experiments show that our proposed MIMO-DBnet not only achieves a comprehensive decent improvement compared to baseline systems, but also maintain the performance on high frequency bands when phase wrapping occurs.
translated by 谷歌翻译