| 刘金华,吴佳韵,饶云波,李永明,俞智慧.融合小波框架和低秩的动态磁共振图像重建新思路[J].电子测量与仪器学报,2024,38(7):55-63 |
| 融合小波框架和低秩的动态磁共振图像重建新思路 |
| New method for dynamic magnetic resonance image reconstructioncombining wavelet frame and low-rank |
| |
| DOI： |
| 中文关键词: 动态磁共振成像 低秩 小波框架 近似点优化梯度方法 压缩感知 |
| 英文关键词:dynamic magnetic resonance imaging (DMRI) low-rank wavelet frame proximal optimized gradient method compressive sensing |
| 基金项目:国家自然科学基金（12161075）、江西省教育厅科技项目(GJJ2201801)资助 |
|
|
| Author | Institution |
| Liu Jinhua | School of Digital Technology Industry, Shangrao Normal University, Shangrao 334001, China |
| Wu Jiayun | School of Digital Technology Industry, Shangrao Normal University, Shangrao 334001, China |
| Rao Yunbo | School of Information and
Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China |
| Li Yongming | School of
Mathematics and Computational Science, Shangrao Normal University, Shangrao 334001, China |
| Yu Zhihui | School of
Mathematics and Computational Science, Shangrao Normal University, Shangrao 334001, China |
|
| 摘要点击次数: 54 |
| 全文下载次数: 310 |
| 中文摘要: |
| 动态磁共振成像(dynamic magnetic resonance imaging, DMRI)是一种通过连续扫描图像获取其随时间和空间变化的影像技术，将压缩感知技术应用于动态磁共振成像，容易导致磁共振图像重建后的视觉质量不够理想。因此，针对压缩感知在DMRI重建上存在的不足，通过 1范数以刻画磁共振图像数据的稀疏性，以及利用低秩描述动态磁共振图像序列的内在相关性，提出了一种基于低秩和稀疏分解的重建模型，有效减少了动态磁共振成像的伪影。在建模阶段，将稀疏成分应用1范数进行建模，对低秩成分利用核范数进行建模。在模型优化求解阶段，引入小波框架正则化方法，将重建模型转化为非光滑凸优化问题，然后使用基于动量加速的近似点优化梯度方法求解该问题。最后，通过在心脏电影、心脏灌输和phantom体膜影像数据上进行实验，验证了所提模型的有效性。结果表明，所提方法在采样率30%时，平均峰值信噪比达到
33.709 0 dB，平均结构相似度达到0.966 0，进一步提升了磁共振图像重建的精度。 |
| 英文摘要: |
| Dynamic magnetic resonance imaging (DMRI) is an imaging technology that acquires images through continuous scanning to capture their changes over time and space. Applying compressed sensing technology to DMRI tends to result in unsatisfactory visual quality of the reconstructed magnetic resonance images. Therefore, to address the deficiencies of compressed sensing in DMRI reconstruction, a reconstruction model based on low-rank and sparse decomposition is proposed by using 1 norm to characterize the sparsity of magnetic resonance image data and utilizing low-rank to describe the intrinsic correlation of dynamic magnetic resonance image sequences. This effectively reduces artifacts in dynamic magnetic resonance imaging. In the modeling phase, the sparse component is modeled using the 1 norm, while the low-rank component is modeled using the nuclear norm. In the model optimization phase, a wavelet framework regularization method is introduced, and the reconstruction model is transformed into a non-smooth convex optimization problem, which is then solved by using a momentum-accelerated proximal gradient method. Finally, experiments are conducted on cardiac cine, cardiac perfusion, and phantom membrane image data to verify the effectiveness of the proposed model. The experimental results show that the average PSNR and the average SSIM of the proposed method reach 33.709 0 dB and 0.966 0 at a sampling ratio of 30%, respectively, which further improves the reconstruction accuracy of the dynamic magnetic resonance image. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
