JZJiajing Zhang

Jiajing Zhang

*This is an algorithmically generated author record based on publicly available information.

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


Jiajing Zhang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • MSAF: A Multi-Level Sensing Adversarial Framework for Signal Recovery in Synthetic Aperture Ultrasound

    by Jiajing Zhang, Bingze Dai, Haotian Guan, Wei-Ning Lee

    Synthetic aperture ultrasound imaging achieves two-way focusing and produces high-quality image formation by coherently combining returning echoes from successive single-element or sub-aperture transmissions across the entire transducer array. To depict transient or fast tissue dynamics, a prominent line of research efforts involves employing a limited number of sub-apertures to approximate full-aperture scans, enabling full-view imaging at high frame rates. However, existing end-to-end approaches predominantly operate in the image domain, which inherently discards phase information. Some studies use radio-frequency or in-phase and quadrature (IQ) domains, but they analyze spatial features frame by frame, thus not fully leveraging the temporal information. Motivated by high-dimensional data inherent to synthetic apertures, this study proposes a multi-level sensing adversarial framework (MSAF) to recover full IQ signals from sparse sub-aperture transmissions. MSAF utilizes sparse apertures by spatiotemporal sensing and constrains the recovered signals by global-attribute sensing. MASF was evaluated on large in vivo human echocardiography datasets and on in vivo unseen echocardiographic views and abdominal images as zero-shot testing sets. Experimental results demonstrated high-fidelity IQ signal recovery, achieving a peak signal-to-noise ratio of 32.80 dB, a structural similarity index of 0.88, a contrast-to-noise ratio of 2.92 dB, and a contrast ratio of 15.46 dB, outperforming all tailored benchmark models. Therefore, MSAF enables sparse-aperture transmissions with high signal quality and data efficiency, making it a potential approach for functional ultrasound imaging.

  • Ultrasound Strain Imaging With Null Subtraction and Coded Plane Waves

    by Bingze Dai, Zhengchang Kou, Jiajing Zhang, Haotian Guan, Michael L. Oelze, Wei-Ning Lee

    Accurate displacement estimation is central to ultrasound strain imaging, which provides a full description of a 2D/3D deformation field to infer elasticity and detect tissue abnormalities. However, lateral displacement estimation has been the major bottleneck, especially with high frame rate requirements, due to inferior spatial resolution, low sampling, and the lack of phase information in that direction. This study focuses on enhancing lateral displacement estimation by improving the lateral resolution of ultrasound multiangle plane-wave imaging through a nonlinear beamformer, Incoherent Compounding Null Subtraction Imaging (IC-NSI). While IC-NSI effectively reduces both main lobe width and secondary lobe levels, its limited penetration depth and reduced speckle coherence are detrimental to tissue motion estimation. We hereby propose to improve the signal-to-noise ratio (SNR) and thus the penetration depth by integrating cascaded dual-polarity waves (CDW) into IC-NSI. We evaluate the feasibility and performance of IC-NSI, with and without CDW, for tissue displacement estimation through Field II and COMSOL simulations of deforming tubes, phantom experiments, and an in vivo study of the human common carotid artery. Both in silico and in vivo carotid ultrasound images obtained by the proposed method exhibited ∼40% improvement in lateral resolution compared with those by coherent plane wave compounding (CPWC). In phantom experiments, the sonographic SNR improved by 14∼17 dB across depths of 20 to 40 mm and had a 32% reduction in mean absolute error in lateral motion estimation in a controlled linear translation scenario. In simulations, our method achieved 13% higher estimation accuracy in lateral displacement under varying strain conditions compared to CPWC. These results demonstrated the conceptual and computational simplicity of the proposed method for high quality ultrasound strain imaging of thin biological structures.


  • Automatic Centroid Angle Measurement From CT Image for Preoperative Rod Design of Robotic-Assisted Screw-Rod System Implantation

    by Jiajing Zhang, Wenqing Zhang, Haodong Liu, Yingying Liu, Ningning Chen, Jianjia Zhang, Changhong Wang

    Robotic-assisted implantation of screw-rod systems serves as an advanced therapy for spinal diseases. A precise curvature fit between rods and spines is critical to postoperative spinal stability. Currently, rod curvature is determined intraoperatively to accommodate screw positions, which is hardly conducive to optimal rod bending and is vulnerable to surgeons’ expertise. To address this challenge, we propose an automated and efficient method for measuring the centroid angle to guide preoperative rod design from CT images. The centroid angle is defined by lines connecting centroids of the upper and lower vertebrae pairs, providing a reliable measurement for spinal deformities. The proposed pipeline includes (1) 3D spine segmentation with multiscale multitask deep learning; (2) vertebrae recognition using graphical morphology; (3) automatic and reproducible centroid angle measurement. Our method is evaluated on both healthy and pathological spines. Compared to manual measurements by professional surgeons, our method achieves an accuracy of 94.50% and 91.93% on adjacent and non-adjacent vertebrae, respectively. A Slicer-based plugin for robotic-assisted screw-rod systems implantation is built, providing a new clinical tool to personalize screw-rod systems consistent with the natural spinal curvature, thereby enhancing biomechanical properties.


  • Hierarchical Perception Adversarial Learning Framework for Compressed Sensing MRI

    by Zhifan Gao, Yifeng Guo, Jiajing Zhang, Tieyong Zeng, Guang Yang

    The long acquisition time has limited the accessibility of magnetic resonance imaging (MRI) because it leads to patient discomfort and motion artifacts. Although several MRI techniques have been proposed to reduce the acquisition time, compressed sensing in magnetic resonance imaging (CS-MRI) enables fast acquisition without compromising SNR and resolution. However, existing CS-MRI methods suffer from the challenge of aliasing artifacts. This challenge results in the noise-like textures and missing the fine details, thus leading to unsatisfactory reconstruction performance. To tackle this challenge, we propose a hierarchical perception adversarial learning framework (HP-ALF). HP-ALF can perceive the image information in the hierarchical mechanism: image-level perception and patch-level perception. The former can reduce the visual perception difference in the entire image, and thus achieve aliasing artifact removal. The latter can reduce this difference in the regions of the image, and thus recover fine details. Specifically, HP-ALF achieves the hierarchical mechanism by utilizing multilevel perspective discrimination. This discrimination can provide the information from two perspectives (overall and regional) for adversarial learning. It also utilizes a global and local coherent discriminator to provide structure information to the generator during training. In addition, HP-ALF contains a context-aware learning block to effectively exploit the slice information between individual images for better reconstruction performance. The experiments validated on three datasets demonstrate the effectiveness of HP-ALF and its superiority to the comparative methods.


  • On the eigenvalue estimation for solution to Lyapunov equation

    by Xingdong Yang, Zhiying Ding, Jiajing Zhang, Suya Sun