计算机应用 ›› 2020, Vol. 40 ›› Issue (12): 3624-3630.DOI: 10.11772/j.issn.1001-9081.2020050670

• 虚拟现实与多媒体计算 • 上一篇    下一篇

基于并行通道-空间注意力机制的腹部MRI影像多尺度超分辨率重建

樊帆, 高媛, 秦品乐, 王丽芳   

  1. 中北大学 大数据学院, 太原 030051
  • 收稿日期:2020-05-20 修回日期:2020-07-06 出版日期:2020-12-10 发布日期:2020-08-14
  • 通讯作者: 高媛(1972-),女,山西太原人,副教授,硕士,主要研究方向:图像处理、人工智能。843933175@qq.com
  • 作者简介:樊帆(1997-),男,山西晋城人,硕士研究生,主要研究方向:深度学习、计算机视觉;秦品乐(1978-),男,山西长治人,教授,博士,主要研究方向:机器视觉、大数据处理;王丽芳(1977-),女,山西长治人,副教授,博士,主要研究方向:机器视觉、大数据处理
  • 基金资助:
    山西省自然科学基金资助项目(201901D111152)。

Abdominal MRI image multi-scale super-resolution reconstruction based on parallel channel-spatial attention mechanism

FAN Fan, GAO Yuan, QIN Pinle, WANG Lifang   

  1. School of Data Science and Technology, North University of China, Taiyuan Shanxi 030051, China
  • Received:2020-05-20 Revised:2020-07-06 Online:2020-12-10 Published:2020-08-14
  • Supported by:
    This work is partially supported by the Natural Science Foundation of Shanxi Province (201901D111152).

摘要: 为了有效解决腹部磁共振成像(MRI)影像在超分辨率重建过程中因高频细节丢失引起的边界不明显、腹部器官显示不清晰以及单模型单尺度重建应用不方便等问题,提出了一种基于并行通道-空间注意力机制的多尺度超分辨率重建算法。首先,构造了并行通道-空间注意力残差块,通过空间注意力模块获取图像重点区域与高频信息的相关性,通过通道注意力模块获取图像各通道对关键信息响应程度的权重,同时拓宽网络的特征提取层以增加流入注意力模块的特征信息;此外,添加了权重归一化层,保证了网络的训练效率;最后,在网络末端应用多尺度上采样层,增加了网络的灵活性和可用性。实验结果表明,相较深层残差通道注意力超分辨率网络(RCAN),所提算法在×2、×3、×4尺度下的峰值信噪比(PSNR)平均提高了0.68 dB。所提算法有效提升了图像的重建质量。

关键词: 超分辨率, 注意力机制, 神经网络, 腹部磁共振成像影像, 多尺度上采样

Abstract: In order to effectively solve the problems of not obvious boundaries, unclear abdominal organ display caused by high-frequency detail loss as well as the inconvenient application of single-model single-scale reconstruction in the super-resolution reconstruction of abdominal Magnetic Resonance Imaging (MRI) images, a multi-scale super-resolution algorithm based on parallel channel-spatial attention mechanism was proposed. Firstly, parallel channel-spatial attention residual blocks were built. The correlation between the key area and high-frequency information was obtained by the spatial attention module, and the channel attention module was used to study the weights of the channels of the image to the key information response degree. At the same time, the feature extraction layer of the network was widened to increase the feature information flowing into the attention module. In addition, the weight normalized layer was added to ensure the training efficiency of the network. Finally, a multi-scale up-sampling layer was applied at the end of the network to increase the flexibility and applicability of the network. Experimental results show that, compared with the image super-resolution using very deep Residual Channel Attention Network (RCAN), the proposed algorithm has the Peak Signal-to-Noise Ratio (PSNR) averagely increased by 0.68 dB at the×2,×3 and×4 scales. The proposed algorithm effectively improves the reconstructed image quality.

Key words: super-resolution, attention mechanism, neural network, abdominal Magnetic Resonance Imaging (MRI) image, multi-scale up-sampling

中图分类号: