Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Zheng Zhong has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Accelerating High b-Value Diffusion-Weighted MRI Using a Convolutional Recurrent Neural Network (CRNN-DWI)

    by Zheng Zhong, Kanghyun Ryu, Jonathan Mao, Kaibao Sun, Guangyu Dan, Shreyas S. Vasanawala, Xiaohong Joe Zhou

    Purpose: To develop a novel convolutional recurrent neural network (CRNN-DWI) and apply it to reconstruct a highly undersampled (up to six-fold) multi-b-value, multi-direction diffusion-weighted imaging (DWI) dataset. Methods: A deep neural network that combines a convolutional neural network (CNN) and recurrent neural network (RNN) was first developed by using a set of diffusion images as input. The network was then used to reconstruct a DWI dataset consisting of 14 b-values, each with three diffusion directions. For comparison, the dataset was also reconstructed with zero-padding and 3D-CNN. The experiments were performed with undersampling rates (R) of 4 and 6. Standard image quality metrics (SSIM and PSNR) were employed to provide quantitative assessments of the reconstructed image quality. Additionally, an advanced non-Gaussian diffusion model was employed to fit the reconstructed images from the different approaches, thereby generating a set of diffusion parameter maps. These diffusion parameter maps from the different approaches were then compared using SSIM as a metric. Results: Both the reconstructed diffusion images and diffusion parameter maps from CRNN-DWI were better than those from zero-padding or 3D-CNN. Specifically, the average SSIM and PSNR of CRNN-DWI were 0.750 ± 0.016 and 28.32 ± 0.69 (R = 4), and 0.675 ± 0.023 and 24.16 ± 0.77 (R = 6), respectively, both of which were substantially higher than those of zero-padding or 3D-CNN reconstructions. The diffusion parameter maps from CRNN-DWI also yielded higher SSIM values for R = 4 (>0.8) and for R = 6 (>0.7) than the other two approaches (for R = 4, <0.7, and for R = 6, <0.65). Conclusions: CRNN-DWI is a viable approach for reconstructing highly undersampled DWI data, providing opportunities to reduce the data acquisition burden.


  • Open Access

    Optimal selection of b-values for differential diagnosis of mediastinal lymph nodes using diffusion-weighted imaging

    by Li-Ping Qi, Zheng Zhong, Ying-Shi Sun, Xiao-Ting Li, Lei Tang, Xiaohong Joe Zhou


  • Open Access

    Multi‐readout DWI with a reduced FOV for studying the coupling between diffusion and T2* relaxation in the prostate

    by Kaibao Sun, Guangyu Dan, Zheng Zhong, Xiaohong Joe Zhou

    Purpose: To develop a DWI sequence with multiple readout echo‐trains in a single shot (multi‐readout DWI) over a reduced FOV, and to demonstrate its ability to achieve high data acquisition efficiency in the study of coupling between diffusion and relaxation in the human prostate.Methods: The proposed multi‐readout DWI sequence plays out multiple EPI readout echo‐trains after a Stejskal‐Tanner diffusion preparation module. Each EPI readout echo‐train corresponded to a distinct effective TE. To maintain a high spatial resolution with a relatively short echo‐train for each readout, a 2D RF pulse was used to limit the FOV. Experiments were performed on the prostate of six healthy subjects to acquire a set of images with three b values (0, 500, and 1000 s/mm2) and three TEs (63.0, 78.8, and 94.6 ms), producing three ADC maps at different TEs and three maps at different b values.Results: Multi‐readout DWI enabled a threefold acceleration without compromising the spatial resolution when compared with a conventional single‐readout sequence. Images with three b values and three TEs were obtained in 3 min 40 s with an adequate SNR (≥ 26.9). The ADC values (1.45 ± 0.13, 1.52 ± 0.14, and 1.58 ± 0.15 ; P < 0.01) exhibited an increasing trend as TEs increased (63.0 ms, 78.8 ms, and 94.6 ms), whereas values (74.78 ± 13.21, 63.21 ± 7.84, and 56.61 ± 5.05 ms; P < 0.01) decreases as the b values increased (0, 500, and 1000 s/mm2).Conclusion: The multi‐readout DWI sequence over a reduced FOV provides a time‐efficient technique to study the coupling between diffusion and relaxation times.


  • Open Access

    Simultaneous multi-segment (SMSeg) EPI over multiple focal regions

    by Kaibao Sun, Zheng Zhong, Guangyu Dan, Kezhou Wang, M Muge Karaman, Qingfei Luo, Xiaohong Joe Zhou

    Objective. This study aimed at developing a simultaneous multi-segment (SMSeg) imaging technique using a two-dimensional (2D) RF pulse in conjunction with echo planar imaging (EPI) to image multiple focal regions. Approach. The SMSeg technique leveraged periodic replicates of the excitation profile of a 2D RF pulse to simultaneously excite multiple focal regions at different locations. These locations were controlled by rotating and scaling transmit k-space trajectories. The resulting multiple isolated focal regions were projected into a composite ‘slice’ for display. GRAPPA-based parallel imaging was incorporated into SMSeg by taking advantage of coil sensitivity variations in both the phase-encoded and slice-selection directions. The SMSeg technique was implemented at 3 T in a single-shot gradient-echo EPI sequence and demonstrated in a phantom and human brains for both anatomic imaging and functional imaging. Main results. In both the phantom and the human brain, SMSeg images from three focal regions were simultaneously acquired. SMSeg imaging enabled up to a six-fold acceleration in parallel imaging without causing appreciable residual aliasing artifacts when compared with a conventional gradient-echo EPI sequence with the same acceleration factor. In the functional imaging experiment, BOLD activations associated with a visuomotor task were simultaneously detected in two non-coplanar segments (each with a size of 240 × 30 mm 2 ), corresponding to visual and motor cortices, respectively. Significance. Our study has demonstrated that SMSeg imaging can be a viable method for studying multiple focal regions simultaneously.


  • SLfRank: Shinnar-Le-Roux Pulse Design With Reduced Energy and Accurate Phase Profiles Using Rank Factorization

    by Frank Ong, Zheng Zhong, Congyu Liao, Michael Lustig, Shreyas S. Vasanawala, John M. Pauly

    The Shinnar-Le-Roux (SLR) algorithm is widely used to design frequency selective pulses with large flip angles. We improve its design process to generate pulses with lower energy (by as much as 26%) and more accurate phase profiles. Concretely, the SLR algorithm consists of two steps: (1) an invertible transform between frequency selective pulses and polynomial pairs that represent Cayley-Klein (CK) parameters and (2) the design of the CK polynomial pair to match the desired magnetization profiles. Because the CK polynomial pair is bi-linearly coupled, the original algorithm sequentially solves for each polynomial instead of jointly. This results in sub-optimal pulses. Instead, we leverage a convex relaxation technique, commonly used for low rank matrix recovery, to address the bilinearity. Our numerical experiments show that the resulting pulses are almost always globally optimal in practice. For slice excitation, the proposed algorithm results in more accurate linear phase profiles. And in general the improved pulses have lower energy than the original SLR pulses.


  • Open Access

    SLfRank: Shinnar-Le-Roux Pulse Design with Reduced Energy and Accurate Phase Profiles using Rank Factorization

    by Frank Ong, Zheng Zhong, Congyu Liao, Michael Lustig, Shreyas Vasanawala, John Pauly

    The Shinnar-Le-Roux (SLR) algorithm is widely used to design frequency selective pulses with large flip angles. We improve its design process to generate pulses with lower energy (by as much as 26%) and more accurate phase profiles. Concretely, the SLR algorithm consists of two steps: (1) an invertible transform between frequency selective pulses and polynomial pairs that represent Cayley-Klein (CK) parameters and (2) the design of the CK polynomial pair to match the desired magnetization profiles. Because the CK polynomial pair is bi-linearly coupled, the original algorithm sequentially solves for each polynomial instead of jointly. This results in sub-optimal pulses. Instead, we leverage a convex relaxation technique, commonly used for low rank matrix recovery, to address the bi-linearity. Our numerical experiments show that the resulting pulses are almost always globally optimal in practice. For slice excitation, the proposed algorithm results in more accurate linear phase profiles. And in general the improved pulses have lower energy than the original SLR pulses.

  • Open Access

    Gradient‐echo‐train ‐based sub‐millisecond periodic event encoded dynamic imaging with random ( k , t )‐space undersampling: k‐t get‐SPEEDI

    by Qingfei Luo, Zheng Zhong, Kaibao Sun, Alessandro Scotti, Xiaohong Joe Zhou

    Purpose The gradient-echo-train-based Sub-millisecond Periodic Event Encoded Dynamic Imaging (get-SPEEDI) technique provides ultrahigh temporal resolutions (similar to 0.6 ms) for detecting rapid physiological activities, but its practical adoption can be hampered by long scan times. This study aimed at developing a more efficient variant of get-SPEEDI for reducing the scan time without degrading temporal resolution or image quality. Methods The proposed pulse sequence, named k-t get-SPEEDI, accelerated get-SPEEDI acquisition by undersampling the k-space phase-encoding lines semi-randomly. At each time frame, k-space was fully sampled in the central region whereas randomly undersampled in the outer regions. A time-series of images was reconstructed using an algorithm based on the joint partial separability and sparsity constraints. To demonstrate the performance of k-t get-SPEEDI, images of human aortic valve opening and closing were acquired with 0.6-ms temporal resolution and compared with those from conventional get-SPEEDI. Results k-t get-SPEEDI achieved a 2-fold scan time reduction over the conventional get-SPEEDI (from similar to 6 to similar to 3 min), while achieving comparable SNRs and contrast-to-noise ratio (CNRs) for visualizing the dynamic process of aortic valve: SNR/CNR approximate to$$ \approx $$ 70/38 vs. 73/39 in the k-t and conventional get-SPEEDI scans, respectively. The time courses of aortic valve area also matched well between these two sequences with a correlation coefficient of 0.86. Conclusions The k-t get-SPEEDI pulse sequence was able to half the scan time without compromising the image quality and ultrahigh temporal resolution. Additional scan time reduction may also be possible, facilitating in vivo adoptions of SPEEDI techniques.

  • Three‐dimensional reduced field‐of‐view imaging (3D‐rFOVI)

    by Kaibao Sun, Zheng Zhong, Guangyu Dan, Muge Karaman, Qingfei Luo, Xiaohong Joe Zhou

    Purpose: This study aimed at developing a 3D reduced field‐of‐view imaging (3D‐rFOVI) technique using a 2D radiofrequency (RF) pulse, and demonstrating its ability to achieve isotropic high spatial resolution and reduced image distortion in echo planar imaging (EPI).Methods: The proposed 3D‐rFOVI technique takes advantage of a 2D RF pulse to excite a slab along the conventional slice‐selection direction (i.e., z‐direction) while limiting the spatial extent along the phase‐encoded direction (i.e., y‐direction) within the slab. The slab is phase‐encoded in both through‐slab and in‐slab phase‐encoded directions. The 3D‐rFOVI technique was implemented at 3T in gradient‐echo and spin‐echo EPI pulse sequences for functional MRI (fMRI) and diffusion‐weighted imaging (DWI), respectively. 3D‐rFOVI experiments were performed on a phantom and human brain to illustrate image distortion reduction, as well as isotropic high spatial resolution, in comparison with 3D full‐FOV imaging.Results: In both the phantom and the human brain, image voxel dislocation was substantially reduced by 3D‐rFOVI when compared with full‐FOV imaging. In the fMRI experiment with visual stimulation, 3D isotropic spatial resolution of (2 × 2 × 2 mm3) was achieved with an adequate signal‐to‐noise ratio (81.5) and blood oxygen level‐dependent (BOLD) contrast (2.5%). In the DWI experiment, diffusion‐weighted brain images with an isotropic resolution of (1 × 1 × 1 mm3) was obtained without appreciable image distortion.Conclusion: This study indicates that 3D‐rFOVI is a viable approach to 3D neuroimaging over a zoomed region.


  • In‐plane simultaneous multisegment imaging using a 2D RF pulse

    by Kaibao Sun, Zheng Zhong, Zhongbiao Xu, Guangyu Dan, M. Muge Karaman, Xiaohong Joe Zhou

    Purpose: To develop an in‐plane simultaneous multisegment (IP‐SMS) imaging technique using a 2D‐RF pulse and to demonstrate its ability to achieve high spatial resolution in EPI while reducing image distortion.Methods: The proposed IP‐SMS technique takes advantage of periodic replicates of the excitation profile of a 2D‐RF pulse to simultaneously excite multiple segments within a slice. These segments were acquired over a reduced FOV and separated using a joint GRAPPA reconstruction by leveraging virtual coils that combined the physical coil sensitivity and 2D‐RF pulse spatial response. Two excitations were used with complementary spatial response profiles to adequately cover a full FOV, producing a full‐FOV image that had the benefits of reduced FOV with high spatial resolution and reduced distortion. The IP‐SMS technique was implemented in a diffusion‐weighted single‐shot EPI sequence. Experimental demonstrations were performed on a phantom and healthy human brain.Results: In the phantom experiment, IP‐SMS enabled a four‐fold acceleration using an eight‐channel coil without causing residual aliasing artifacts. In the human brain experiment, diffusion‐weighted images with high in‐plane resolution (1 × 1 mm2) and substantially reduced image distortion were obtained in all imaging planes in comparison with a commercial diffusion‐weighted EPI sequence. The capability of IP‐SMS for contiguous whole‐brain coverage was also demonstrated.Conclusion: The proposed IP‐SMS technique can realize the benefits of reduced‐FOV imaging while achieving a full‐FOV coverage with good image quality and time efficiency.


  • Open Access

    Diffusion in Sephadex Gel Structures: Time Dependency Revealed by Multi-Sequence Acquisition over a Broad Diffusion Time Range

    by Guangyu Dan, Weiguo Li, Zheng Zhong, Kaibao Sun, Qingfei Luo, Richard L. Magin, Xiaohong Joe Zhou, M. Muge Karaman

    It has been increasingly reported that in biological tissues diffusion-weighted MRI signal attenuation deviates from mono-exponential decay, especially at high b-values. A number of diffusion models have been proposed to characterize this non-Gaussian diffusion behavior. One of these models is the continuous-time random-walk (CTRW) model, which introduces two new parameters: a fractional order time derivative α and a fractional order spatial derivative β. These new parameters have been linked to intravoxel diffusion heterogeneities in time and space, respectively, and are believed to depend on diffusion times. Studies on this time dependency are limited, largely because the diffusion time cannot vary over a board range in a conventional spin-echo echo-planar imaging sequence due to the accompanying T2 decays. In this study, we investigated the time-dependency of the CTRW model in Sephadex gel phantoms across a broad diffusion time range by employing oscillating-gradient spin-echo, pulsed-gradient spin-echo, and pulsed-gradient stimulated echo sequences. We also performed Monte Carlo simulations to help understand our experimental results. It was observed that the diffusion process fell into the Gaussian regime at extremely short diffusion times whereas it exhibited a strong time dependency in the CTRW parameters at longer diffusion times.