论文标题
几何方法增加了MR重建的深神经网络的表现性
Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
论文作者
论文摘要
最近，已经对深度学习方法进行了广泛的研究，以从加速磁共振图像（MRI）采集中重建图像。尽管这些方法与压缩传感MRI（CS-MRI）相比提供了显着的性能增长，但尚不清楚如何选择合适的网络体系结构以平衡网络复杂性和性能之间的权衡。最近，结果表明，编码器卷积神经网络（CNN）可以解释为类似线性基依的表示，其特定表示由给定输入图像的relu激活模式确定。因此，表达性或表示能力取决于分段线性区域的数量。作为这种几何理解的扩展，本文提出了一种使用引导模块的引导和子网络聚集的系统几何方法，以提高基本神经网络的表达性。我们的方法可以在可以以端到端方式训练的K空间域和图像域中实现。实验结果表明，提出的方案会显着提高重建性能，而复杂性可忽略不计。
Recently, deep learning approaches have been extensively investigated to reconstruct images from accelerated magnetic resonance image (MRI) acquisition. Although these approaches provide significant performance gain compared to compressed sensing MRI (CS-MRI), it is not clear how to choose a suitable network architecture to balance the trade-off between network complexity and performance. Recently, it was shown that an encoder-decoder convolutional neural network (CNN) can be interpreted as a piecewise linear basis-like representation, whose specific representation is determined by the ReLU activation patterns for a given input image. Thus, the expressivity or the representation power is determined by the number of piecewise linear regions. As an extension of this geometric understanding, this paper proposes a systematic geometric approach using bootstrapping and subnetwork aggregation using an attention module to increase the expressivity of the underlying neural network. Our method can be implemented in both k-space domain and image domain that can be trained in an end-to-end manner. Experimental results show that the proposed schemes significantly improve reconstruction performance with negligible complexity increases.
