《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (3): 938-945.DOI: 10.11772/j.issn.1001-9081.2021040629

• 多媒体计算与计算机仿真 • 上一篇    

基于多感受野的生成对抗网络医学MRI影像超分辨率重建

刘朋伟1,2,3, 高媛1,2,3(), 秦品乐1,2,3, 殷喆1,2,3, 王丽芳1,2,3   

  1. 1.山西省医学影像与数据分析工程研究中心(中北大学), 太原 030051
    2.中北大学 大数据学院, 太原 030051
    3.山西省医学影像人工智能工程技术研究中心(中北大学), 太原 030051
  • 收稿日期:2021-04-21 修回日期:2021-06-23 接受日期:2021-06-23 发布日期:2022-04-09 出版日期:2022-03-10
  • 通讯作者: 高媛
  • 作者简介:刘朋伟(1996—),男,陕西咸阳人,硕士研究生,CCF会员,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
    殷喆(1997—),女,山西大同人,硕士研究生,主要研究方向:图像融合、深度学习
    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)

Medical MRI image super-resolution reconstruction based on multi-receptive field generative adversarial network

Pengwei LIU1,2,3, Yuan GAO1,2,3(), Pinle QIN1,2,3, Zhe YIN1,2,3, Lifang WANG1,2,3   

  1. 1.Shanxi Medical Imaging and Data Analysis Engineering Research Center(North University of China),Taiyuan Shanxi 030051,China
    2.School of Data Science and Technology,North University of China,Taiyuan Shanxi 030051,China
    3.Shanxi Medical Imaging Artificial Intelligence Engineering Technology Research Center(North University of China),Taiyuan Shanxi 030051,China
  • Received:2021-04-21 Revised:2021-06-23 Accepted:2021-06-23 Online:2022-04-09 Published:2022-03-10
  • Contact: Yuan GAO
  • About author:LIU Pengwei, born in 1996, M. S. candidate. His research interests include deep learning, computer vision.
    QIN Pinle, born in 1978, Ph. D., professor. His research interests include machine vision, big data processing.
    YIN Zhe, born in 1997, M. S. candidate. Her research interests include image fusion, deep learning
    WANG Lifang, born in 1977, Ph. D., associate professor. Her research interests include machine vision, big data processing.
  • Supported by:
    Natural Science Foundation of Shanxi Province(201901D111152)

摘要:

针对医学磁共振成像(MRI)过程中由于噪声、成像技术和成像原理等干扰因素引起的图像细节丢失、纹理不清晰等问题,提出了基于多感受野的生成对抗网络医学MRI影像超分辨率重建算法。首先,利用多感受野特征提取块获取不同感受野下图像的全局特征信息,为避免感受野过小或过大导致图像的细节纹理丢失,将每组特征分为两组,其中一组用于反馈不同尺度感受野下的全局特征信息,另一组用于丰富下一组特征的局部细节纹理信息;然后,使用多感受野特征提取块构建特征融合组,并在每个特征融合组中添加空间注意力模块,充分获取图像的空间特征信息,减少了浅层和局部特征在网络中的丢失,在图像的细节上取得了更逼真的还原度;其次,将低分辨率图像的梯度图转化为高分辨率图像的梯度图辅助重建超分辨率图像;最终将恢复后的梯度图集成到超分辨率分支中,为超分辨率重建提供结构先验信息,有助于生成高质量的超分辨率图像。实验结果表明,相比基于梯度引导的结构保留超分辨率算法(SPSR),所提算法在×2、×3、×4尺度下的峰值信噪比(PSNR)分别提升了4.8%、2.7%、3.5%,重建出的医学MRI影像纹理细节更加丰富、视觉效果更加逼真。

关键词: 超分辨率, 多感受野, 空洞卷积, 空间注意力机制, 梯度图

Abstract:

To solve the problems of image detail loss and unclear texture caused by interference factors such as noise, imaging technology and imaging principles in the medical Magnetic Resonance Imaging (MRI) process, a multi-receptive field generative adversarial network for medical MRI image super-resolution reconstruction was proposed. First, the multi-receptive field feature extraction block was used to obtain the global feature information of the image under different receptive fields. In order to avoid the loss of detailed texture due to too small or too large receptive fields, each set of features was divided into two groups, and one of which was used to feedback global feature information under different scales of receptive fields, and the other group was used to enrich the local detailed texture information of the next set of features; then, the multi-receptive field feature extraction block was used to construct feature fusion group, and spatial attention module was added to each feature fusion group to adequately obtain the spatial feature information of the image, reducing the loss of shallow and local features in the network, and achieving a more realistic degree in the details of the image. Secondly, the gradient map of the low-resolution image was converted into the gradient map of the high-resolution image to assist the reconstruction of the super-resolution image. Finally, the restored gradient map was integrated into the super-resolution branch to provide structural prior information for super-resolution reconstruction, which was helpful to generate high quality super-resolution images. The experimental results show that compared with the Structure-Preserving Super-Resolution with gradient guidance (SPSR) algorithm, the proposed algorithm improves the Peak Signal-to-Noise Ratio (PSNR) by 4.8%, 2.7% and 3.5% at ×2, ×3 and ×4 scales, respectively, and the reconstructed medical MRI images have richer texture details and more realistic visual effects.

Key words: super-resolution, multi-receptive field, dilated convolution, spatial attention mechanism, gradient map

中图分类号: