Zhaoyang Jin
Hangzhou Dianzi University
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Zhaoyang Jin.
IEEE Transactions on Biomedical Engineering | 2015
Yang Yang; Feng Liu; Zhaoyang Jin; Stuart Crozier
Goal: Random phase-encode undersampling of Cartesian k-space trajectories is widely implemented in compressed sensing (CS) MRI. However, its one-dimensional (1-D) randomness inherently introduces large coherent aliasing artefacts along the undersampled direction in the reconstruction and, thus, degrades the image quality. This paper proposes a novel reconstruction scheme to reduce the 1-D undersampling-induced aliasing artefacts. Methods: The proposed reconstruction progress is separated into two steps in our new algorithm. In step one, we transfer the original two-dimensional (2-D) image reconstruction into a parallel 1-D signal reconstruction procedure, which takes advantage of the superior incoherence property in the phase direction. In step two, using the new k-space data obtained from the 1-D reconstructions, we implement a follow-up 2-D CS reconstruction to produce a better solution, which exploits the inherent correlations between the adjacent lines of 1-D reconstructed signals. Results: We evaluated the performance on various cases of typical MR images, including cardiac cine, brain, foot, and angiogram at the reduction factor up to 10 and compared the results with the conventional CS method. Experiments using the proposed method demonstrated faithful reconstruction of the MR images. Conclusion: Compared with conventional method, the new method achieves more accurate reconstruction results with 2-5 dB gain in peak SNR and higher structural similarity index. Significance: The proposed method improves image quality of the reconstructions and suppresses the coherent artefacts introduced by the random phase-encode undersampling.
biomedical engineering and informatics | 2014
Jinsong Zhang; Zhaoyang Jin; Haihui Ye; Feng Liu
Motion prediction algorithms are often used in dynamic magnetic resonance imaging to improve the compressed sensing based reconstruction. Previously, the difference calculation (DC) between the current frame (to be reconstructed) and the estimated frame was used as sparse residual signals. In order to obtain sparser signal, an improved Motion Estimation (ME) and Motion Compensation (MC) method was proposed to predict the current frame from previous reconstructed frames with an extrapolation procedure. An overlapped block motion compensation algorithm was used to suppress the block artifacts. The sparse residual signal was used to reconstruct the current frame using an iterative soft thresholding algorithm. The experiment results show that, the ME/MC prediction can improve the quality of reconstructed frames at slight additional computational cost. For the case that ME/MC combined with previous DC method, a high quality image reconstruction can be achieved with relatively small time consumption.
biomedical engineering and informatics | 2013
Qinjie Ruan; Zhaoyang Jin; Feng Liu; Ping Xu; Xiaoping Lai
Compressed Sensing (CS) increases the speed of MRI by reducing the sampling data. k-t FOCUSS is an effective CS algorithm for image reconstruction in dynamic MRI. In this method, in order to further improve its performance, a predictive frame is first obtained using the Motion Estimation (ME) and Motion Compensation (MC) algorithms, and the quality of reconstructed images can then be enhanced by the study of sparsity of the residuals based on the improved predictive frame. However, traditional MC algorithm usually causes block artifacts. In this work, an Overlapped Block Motion Compensation (OBMC) scheme was used to overcome this problem. Two reference frames, located at systole and diastole periods, were both acquired to improve the predication accuracy. Experimental results show that, the k-t FOCUSS with ME/MC and OBMC can successfully suppress the image artifacts generated by the standard k-t FOCUSS with ME/MC.
biomedical engineering and informatics | 2012
Wei Chen; Zhaoyang Jin; Feng Liu; Yiping P. Du
Long scan time has hampered susceptibility weighted imaging (SWI) in routine clinical application to diagnose brain diseases related to venous vasculature. Compressed sensing (CS) was demonstrated to significantly reduce scan time of SWI by exploiting signal sparsity in wavelet domain. However the reconstruction time of CS based on wavelet sparsity is usually time consuming. In this study, the feasibility of applying CS in SWI with singular value decomposition (SVD)-based sparsity basis was investigated. It was found that CS reconstruction based on SVD sparsity basis can achieve reasonably high computing speed than that of wavelet-based sparsity basis, while still achieving accurate image reconstruction.
biomedical engineering and informatics | 2012
Zhaoyang Jin; Qing-San Xiang; Yiping P. Du
Susceptibility weighted imaging (SWI) in magnetic resonance imaging (MRI) has shown great merits in diagnosing brain diseases related to venous vasculature. A relatively long echo time (TE) is typically used for optimal venous contrast. This often leads to a long scan time for high resolution SWI, and can hamper routine clinical applications. Recently, compressed sensing (CS) holds considerable promise to accelerate MRI data acquisition by exploiting signal sparsity. In this study, we investigated feasibility of applying CS to SWI data acquisition to reduce scan time. It was found that CS can achieve reasonably high quality SWI reconstruction using only small fractional k-space coverage.
Magnetic Resonance in Medicine | 2016
Zhaoyang Jin; Haihui Ye; Yiping P. Du; Qing-San Xiang
To improve the image quality of skipped phase encoding and edge deghosting (SPEED) by exploiting several sparsifying transforms.
biomedical engineering and informatics | 2015
Changjiu Zhang; Zhaoyang Jin; Haihui Ye; Feng Liu
Traditional CS with dictionary learning (DL) algorithm can be applied in reconstruction for dynamic cardiac imaging (DCI), which is realized by multi-slice two-dimensional format (2D-DLDCI) or directly three-dimensional format (3D-DLDCI). It was reported that dual-dictionary learning algorithm can improve the reconstruction quality for the 3D magnetic resonance imaging (MRI) by introducing prior information and inter-frame correlation. In this study, dual-dictionary learning algorithm was applied in dynamic cardiac imaging (Dual-DLDCI) by exploring the symmetry of the cardiac cycle. High resolution dictionary was trained from the fully acquired previous frames within a period of relaxation, and low resolution dictionary was trained from the under-sampled frames. The patches for traditional 2D dictionary were replaced by the blocks to utilize the spatial correlation among frames. The high resolution dictionary instead of low resolution dictionary was used in the iterative reconstruction to provide prior information. The simulation and experiment results showed that, the Dual-DLDCI algorithm achieves much better reconstruction quality than the other two algorithms.
biomedical engineering and informatics | 2012
Zhaoyang Jin; Yiping P. Du
Magnetic resonance angiography (MRA) has significant clinical applications in the diagnosis of brain diseases related to arteries vasculature. It is often performed as a three dimensional data acquisition and, therefore, long scan time is typicall required. Recently, compressed sensing holds considerable promise to accelerate MRI data acquisition by exploiting signal sparsity. In this study, partial echo compressed sensing (PECS) method is investigated to reduce the MRA data acquisition time. Partial echo combined with random undersampling along phase encoding directions is proposed to acquire MRA data, projection onto convex set (POCS) combined with soft thresholding is used to approximate the undersampled k-space data, followed by a nonlinear reconstruction to further improve the image quality. The results show that PECS method can achieve reasonably high quality MRA reconstruction using only a small fractional k-space coverage.
international congress on image and signal processing | 2017
Zhaoyang Jin; Yuan Hu; Qing-San Xiang; Yiping P. Du
international congress on image and signal processing | 2017
Qiushi Meng; Zhaoyang Jin