VolumeNet: A Lightweight Parallel Network for Super-Resolution of MR and CT Volumetric Data
VolumeNet: A Lightweight Parallel Network for Super-Resolution of MR and CT Volumetric Data
复制标题
VolumeNet：用于 MR 和 CT 体积数据超分辨率的轻量级并行网络
DOI：
10.1109/tip.2021.3076285
复制
发表时间：
2021-01-01
影响因子：
10.6
通讯作者：
Chen, Yen-Wei
中科院分区：
文献类型：
--
作者：
Li, Yinhao;Iwamoto, Yutaro;Chen, Yen-Wei
基于深度学习的超分辨率（SR）技术在计算机视觉领域普遍取得了优异的性能。最近，已经证明，用于医学体积数据的三维（3D）SR提供比常规二维（2D）处理更好的视觉结果。然而，由于参数数量多、训练样本数量少，加深和拓宽3D网络会显着增加训练难度。因此，我们提出了一个3D卷积神经网络（CNN）的磁共振（MR）和计算机断层扫描（CT）体积数据的SR称为并行连接的卷积神经网络。我们基于组卷积和特征聚合构建了一个并行连接结构，以构建一个尽可能宽的3D CNN，并且参数很少。因此，该模型彻底学习了更多的特征图，具有更大的感受野。此外，为了进一步提高准确性，我们提出了一个高效版本的MPENELNET（称为VolumeNet），它减少了参数的数量，并使用一个称为队列模块的轻量级构建块模块来深化MPENELNET。与大多数基于深度卷积的轻量级CNN不同，队列模块主要使用可分离的2D交叉通道卷积来构建。因此，由于全信道融合，网络参数的数量和计算复杂度可以显着减少，同时保持精度。实验结果表明，所提出的VolumeNet显着减少了模型参数的数量，并实现了高精度的结果相比，国家的最先进的方法在任务的大脑MR图像SR，腹部CT图像SR，超分辨率7T的图像重建从他们的3T同行。
Deep learning-based super-resolution (SR) techniques have generally achieved excellent performance in the computer vision field. Recently, it has been proven that three-dimensional (3D) SR for medical volumetric data delivers better visual results than conventional two-dimensional (2D) processing. However, deepening and widening 3D networks increases training difficulty significantly due to the large number of parameters and small number of training samples. Thus, we propose a 3D convolutional neural network (CNN) for SR of magnetic resonance (MR) and computer tomography (CT) volumetric data called ParallelNet using parallel connections. We construct a parallel connection structure based on the group convolution and feature aggregation to build a 3D CNN that is as wide as possible with a few parameters. As a result, the model thoroughly learns more feature maps with larger receptive fields. In addition, to further improve accuracy, we present an efficient version of ParallelNet (called VolumeNet), which reduces the number of parameters and deepens ParallelNet using a proposed lightweight building block module called the Queue module. Unlike most lightweight CNNs based on depthwise convolutions, the Queue module is primarily constructed using separable 2D cross-channel convolutions. As a result, the number of network parameters and computational complexity can be reduced significantly while maintaining accuracy due to full channel fusion. Experimental results demonstrate that the proposed VolumeNet significantly reduces the number of model parameters and achieves high precision results compared to state-of-the-art methods in tasks of brain MR image SR, abdomen CT image SR, and reconstruction of super-resolution 7T-like images from their 3T counterparts.