南方医科大学学报

南方医科大学学报 ›› 2022, Vol. 42 ›› Issue (12): 1799-1806.doi: 10.12122/j.issn.1673-4254.2022.12.07

• • 上一篇    下一篇

定量磁化率成像中磁化率重建伪影的清除：基于多通道输入的卷积神经网络方法

斯文彬，冯衍秋   

  1. 南方医科大学生物医学工程学院，广东 广州 510515；医学图像处理广东省重点实验室与医学成像诊断技术广东省工程实验室，广东 广州 510515
  • 出版日期:2022-12-20 发布日期:2023-01-12

A multi-channel input convolutional neural network for artifact reduction in quantitative susceptibility mapping

SI Wenbin, FENG Yanqiu   

  1. School of Biomedical Engineering, Guangdong Provincial Key Laboratory of Medical Image Processing & Guangdong Provincial Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou 510515, China
  • Online:2022-12-20 Published:2023-01-12

RichHTML

20

PDF

266

摘要： 目的 基于深度学习方法消除定量磁化率成像（QSM）过程中出现的各类磁化率相关伪影。方法 为消除磁化率差异较大的分界面上出现的伪影，本文提出了一种基于多通道输入的卷积神经网络方法（MAR-CNN），用于单方向偶极子反卷积QSM重建。该方法根据磁化率的阈值与静脉掩膜将原始组织场分成两个分量，与原始组织场拼接作为MAR-CNN的三通道输入。实验将MAR-CNN与三种基于模型的方法，阈值截断k空间除法（TKD），形态学的偶极子反卷积方法（MEDI）和改进的稀疏线性方程最小二乘法（iLSQR）和一种深度学习方法（QSMnet）进行比较，并使用高频误差范数、峰值信噪比、归一化均方根误差和结构相似性指数进行定量评估。结果 在健康志愿者中，与TKD、MEDI、iLSQR和QSMnet相比，MAR-CNN重建图像的峰值信噪比最高（43.12±1.19）、归一化均方根误差最小（51.98±3.65）。与QSMnet相比，MAR-CNN在所有四个量化指标上都是更优的，且具有显著性差异（P<0.05）。对于仿真的出血患者，MAR-CNN在高磁化率的出血病灶周围产生的阴影伪影更少。结论 本文提出的多通道输入卷积神经网络QSM重建方法可提高定量磁化率重建的准确度并有效消除QSM伪影。

关键词: 定量磁化率成像；深度学习；卷积神经网络；图像重建

Abstract: Objective To develop a deep learning-based QSM reconstruction method for reducing artifacts to improve the accuracy of magnetic susceptibility results. Methods To eliminate artifacts caused by susceptibility interfaces with gigantic differences, we propose a multi-channel input convolutional neural network for artifact reduction (MAR-CNN) for solving the dipole inversion problem in QSM. In this neural network, the original tissue field was first separated into two components, which were subsequently imported as additional channels into a multi-channel 3D U-Net. MAR-CNN was compared with 3 conventional model-based methods, namely truncated k-space deconvolution (TKD), morphology enabled dipole inversion (MEDI), and improved sparse linear equation and least squares method (iLSQR), and with a deep learning method (QSMnet). High-frequency error norm, peak signal-to-noise ratio, normalized root mean squared error, and structure similarity index were reported for quantitative comparisons. Results Experiments on healthy volunteers demonstrated that the results obtained using MAR-CNN had superior peak signal-to-noise ratio (43.12±1.19) and normalized root mean squared error (51.98±3.65) to those of TKD, MEDI, iLSQR and QSMnet. MAR-CNN outperformed QSMnet reconstruction on all the 4 quantitative metrics with significant differences (P<0.05). Experiment on data of simulated hemorrhagic lesion demonstrated that MAR-CNN produced less shadow artifacts around the bleeding lesion than the other 4 methods. Conclusion The proposed MAR- CNN for artifact reduction is capable of improving the accuracy of deep learning- based QSM reconstruction to effectively reduce artifacts.

Key words: quantitative susceptibility mapping; deep learning; convolutional neural networks; image reconstruction