QWQing Wu

Qing Wu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Qing Wu has a total of 57 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Physics-Informed Implicit Neural Representations in Biomedical Tomography: Principles, Applications, and Reliability

    by Yuyao Zhang, Qing Wu, Tianqi Yu, Xuanyu Tian, Xin Shen, Xin Li, Jiayue Chu, Guoyan Lao, Haoyuan Le, Chenhe Du, et al.

  • A Real-Time Neural Representation via Algorithm-Hardware Synergy for Sparse-View CT Reconstruction

    by Xin Li, Haochuan Wan, Kangjie Long, Qing Wu, Chenhe Du, Ying Su, Zhe Luo, Xin Lou, Yuyao Zhang

    Sparse-view computed tomography (SVCT) is an advancement in computed tomography (CT) technology that aims to reduce the radiation dose during imaging. Reconstructing high-quality images from sparse-view (SV) projections is an ill-posed inverse problem. Recently, implicit neural representations (INRs) as a self-supervised paradigm for solving underdetermined inverse problems have demonstrated excellent performance in SVCT reconstruction. However, since INR-based approaches rely on subject-specific training, they require a significant investment of time to optimize from scratch. Consequently, previous INR methods have not been able to meet the requisite timeliness of reconstruction. In our work, we propose RTSyner, an algorithm-hardware collaboration framework that facilitates the real-time efficiency of CT reconstruction. On the algorithmic side, we introduce an efficient coordinate-based feature module that exploits the local latent features as a positional external condition, leveraging the limited structural information of corrupted images derived from the sensory domain. By fusing latent features and coordinate information, the model learns a neural representation of the final tomographic image. On the hardware side, we design a dedicated hardware architecture with a customized algorithm flow to improve reconstruction speed and reduce power consumption. Furthermore, we improve the efficiency of model inference through model quantization, which also facilitates the subsequent deployment of hardware. Our extensive experimental results demonstrate that the RTSyner based on neural representation has achieved real-time SVCT reconstruction through the synergistic acceleration of the algorithm and hardware. We further explore its application potential via volume reconstructions under more complex acquisition geometries.


  • BentRay-NeRF: Bent-Ray Neural Radiance Fields for Robust Speed-of-Sound Imaging in Ultrasound Computed Tomography

    by Shilong Cui, Qing Wu, Yiming Huang, Haizhao Dai, Yuyao Zhang, Jingyi Yu, Xiran Cai

    Ultrasound computed tomography (USCT) is a promising technique for breast cancer detection, because of its quantitative imaging capability of the speed-of-sound (SOS) of soft tissues and the fact that malignant breast lesions often have a higher SOS compared to healthy tissues in the human breast. Compared to waveform inversion-based USCT, bent-ray tracing USCT is relatively less computationally expensive, which particularly suits breast cancer screening in a large population. However, SOS image reconstruction using bent-ray tracing in USCT is a highly ill-conditioned problem, making it susceptible to measurement errors. This presents significant challenges in achieving stable and high-quality reconstructions. In this study, we show that using implicit neural representation (INR), the ill-conditioned problem can be well mitigated, and stable reconstruction is achievable. This INR approach uses a multi-layer perceptron with hash encoding to model the slowness map as a continuous function, to better regularize the inverse problem and has been shown more effective than classical approaches of solely adding regularization terms in the loss function. Thereby, we propose the Bent Ray Neural Radiance Fields (BentRay-NeRF) method for SOS image reconstruction to address the aforementioned challenges in classical SOS image reconstruction methods, such as the Gauss-Newton method. In silico and in vitro experiments showed that BentRay-NeRF has remarkably improved performance compared to the classical method in many aspects, including the image quality and the robustness of the inversion to different acquisition settings in the presence of measurement errors.


  • Top Cited Papers

    Spatiotemporal Implicit Neural Representation for Unsupervised Dynamic MRI Reconstruction

    by Jie Feng, Ruimin Feng, Qing Wu, Xin Shen, Lixuan Chen, Xin Li, Li Feng, Jingjia Chen, Zhiyong Zhang, Chunlei Liu, et al.

    Supervised Deep-Learning (DL)-based reconstruction algorithms have shown state-of-the-art results for highly-undersampled dynamic Magnetic Resonance Imaging (MRI) reconstruction. However, the requirement of excessive high-quality ground-truth data hinders their applications due to the generalization problem. Recently, Implicit Neural Representation (INR) has emerged as a powerful DL-based tool for solving the inverse problem by characterizing the attributes of a signal as a continuous function of corresponding coordinates in an unsupervised manner. In this work, we proposed an INR-based method to improve dynamic MRI reconstruction from highly undersampled k -space data, which only takes spatiotemporal coordinates as inputs and does not require any training on external datasets or transfer-learning from prior images. Specifically, the proposed method encodes the dynamic MRI images into neural networks as an implicit function, and the weights of the network are learned from sparsely-acquired ( k , t)-space data itself only. Benefiting from the strong implicit continuity regularization of INR together with explicit regularization for low-rankness and sparsity, our proposed method outperforms the compared state-of-the-art methods at various acceleration factors. E.g., experiments on retrospective cardiac cine datasets show an improvement of 0.6–2.0 dB in PSNR for high accelerations (up to 40.8×). The high-quality and inner continuity of the images provided by INR exhibit great potential to further improve the spatiotemporal resolution of dynamic MRI. The code is available at: https://github.com/AMRILab/INR_for_DynamicMRI.


  • IMJENSE: Scan-Specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI

    by Ruimin Feng, Qing Wu, Jie Feng, Huajun She, Chunlei Liu, Yuyao Zhang, Hongjiang Wei

    Parallel imaging is a commonly used technique to accelerate magnetic resonance imaging (MRI) data acquisition. Mathematically, parallel MRI reconstruction can be formulated as an inverse problem relating the sparsely sampled k-space measurements to the desired MRI image. Despite the success of many existing reconstruction algorithms, it remains a challenge to reliably reconstruct a high-quality image from highly reduced k-space measurements. Recently, implicit neural representation has emerged as a powerful paradigm to exploit the internal information and the physics of partially acquired data to generate the desired object. In this study, we introduced IMJENSE, a scan-specific implicit neural representation-based method for improving parallel MRI reconstruction. Specifically, the underlying MRI image and coil sensitivities were modeled as continuous functions of spatial coordinates, parameterized by neural networks and polynomials, respectively. The weights in the networks and coefficients in the polynomials were simultaneously learned directly from sparsely acquired k-space measurements, without fully sampled ground truth data for training. Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms. With extremely limited calibration data, IMJENSE is more stable than supervised calibrationless and calibration-based deep-learning methods. Results show that IMJENSE robustly reconstructs the images acquired at 5× and 6× accelerations with only 4 or 8 calibration lines in 2D Cartesian acquisitions, corresponding to 22.0% and 19.5% undersampling rates. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.


  • Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography

    by Qing Wu, Ruimin Feng, Hongjiang Wei, Jingyi Yu, Yuyao Zhang

    Sparse-view Computed Tomography (SVCT) has great potential for decreasing patient radiation exposure dose during scanning. In this work, we propose a Self-supervised COordinate Projection nEtwork (SCOPE) to reconstruct the artifact-free CT image from the acquired SV sinogram by solving the inverse problem of tomography imaging. To solve the under-determined inverse imaging problem, we first introduce an implicit neural representation (INR) network to constrain the solution space via image continuity prior. And inspired by the relationship between linear algebra and inverse problems, we propose a novel re-projection strategy to generate a dense view sinogram from the initial solution, which significantly improves the rank of the linear equation system and produces a more stable CT image solution space. Specially, the desired CT image is represented as an implicit function of the two-dimensional spatial coordinate to directly approximate the SV sinogram through the CT imaging forward model. Then, a dense-view sinogram is generated from the fine-trained INR network. The final CT reconstruction is reconstructed by applying Filtered Back Projection (FBP) to the generated dense-view sinogram. Additionally, we integrate the recent hash encoding into our SCOPE model, which efficiently accelerates the model training process. We evaluate SCOPE in parallel and fan X-ray beam SVCT reconstruction tasks. Our experiment results demonstrate that the re-projection strategy significantly improves the image reconstruction quality (+3 dB for PSNR at least). The proposed SCOPE model provides state-of-the-art reconstruction results compared to two latest INR-based methods and two well-popular supervised DL methods for the SV CT image reconstruction.


  • An Energy-Efficient Accelerator for Medical Image Reconstruction From Implicit Neural Representation

    by Chaolin Rao, Qing Wu, Pingqiang Zhou, Jingyi Yu, Yuyao Zhang, Xin Lou

    This work presents an energy-efficient accelerator for medical image reconstruction from implicit neural representation (INR). The accelerator implements an INR-based algorithm to deliver high-quality medical image reconstruction with arbitrary resolution from a compact implicit format. In particular, we propose a dedicated hardware architecture based on an optimized computation flow for the INR-based reconstruction algorithm, which co-designs data reuse and computation load. The proposed architecture takes in the coordinate of the intersection of three scans and outputs all the voxel intensities, minimizing the data movement between on-chip and off-chip. To validate the proposed accelerator, we build a proof-of-concept prototype demonstration system using field programmable gate array (FPGA). We also map our design to 40nm CMOS technology to measure the performance of the proposed accelerator. The implementation results show that, running at 400MHz, the proposed accelerator is capable of processing medical images with $256\times 256$ resolution in real-time at 26.3 frames per second (FPS), with a power consumption of only 795 mW. Comparison results show that the performance, as well as the energy efficiency of the proposed accelerator, outperforms the central processing unit (CPU)-based and graphic processing unit (GPU)-based implementations.


  • Open Access

    An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representation

    by Qing Wu, Yuwei Li, Yawen Sun, Yan Zhou, Hongjiang Wei, Jingyi Yu, Yuyao Zhang

    High Resolution (HR) medical images provide rich anatomical structure details to facilitate early and accurate diagnosis. In MRI, restricted by hardware capacity, scan time, and patient cooperation ability, isotropic 3D HR image acquisition typically requests long scan time and, results in small spatial coverage and low SNR. Recent studies showed that, with deep convolutional neural networks, isotropic HR MR images could be recovered from low-resolution (LR) input via single image super-resolution (SISR) algorithms. However, most existing SISR methods tend to approach a scale-specific projection between LR and HR images, thus these methods can only deal with a fixed up-sampling rate. For achieving different up-sampling rates, multiple SR networks have to be built up respectively, which is very time-consuming and resource-intensive. In this paper, we propose ArSSR, an Arbitrary Scale Super-Resolution approach for recovering 3D HR MR images. In the ArSSR model, the reconstruction of HR images with different up-scaling rates is defined as learning a continuous implicit voxel function from the observed LR images. Then the SR task is converted to represent the implicit voxel function via deep neural networks from a set of paired HR-LR training examples. The ArSSR model consists of an encoder network and a decoder network. Specifically, the convolutional encoder network is to extract feature maps from the LR input images and the fully-connected decoder network is to approximate the implicit voxel function. Due to the continuity of the learned function, a single ArSSR model can achieve arbitrary up-sampling rate reconstruction of HR images from any input LR image after training. Experimental results on three datasets show that the ArSSR model can achieve state-of-the-art SR performance for 3D HR MR image reconstruction while using a single trained model to achieve arbitrary up-sampling scales.

  • Top Cited Papers

    An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representation

    by Qing Wu, Yuwei Li, Yawen Sun, Yan Zhou, Hongjiang Wei, Jingyi Yu, Yuyao Zhang

    High Resolution (HR) medical images provide rich anatomical structure details to facilitate early and accurate diagnosis. In magnetic resonance imaging (MRI), restricted by hardware capacity, scan time, and patient cooperation ability, isotropic 3-dimensional (3D) HR image acquisition typically requests long scan time and, results in small spatial coverage and low signal-to-noise ratio (SNR). Recent studies showed that, with deep convolutional neural networks, isotropic HR MR images could be recovered from low-resolution (LR) input via single image super-resolution (SISR) algorithms. However, most existing SISR methods tend to approach scale-specific projection between LR and HR images, thus these methods can only deal with fixed up-sampling rates. In this paper, we propose ArSSR, an Ar bitrary S cale S uper- R esolution approach for recovering 3D HR MR images. In the ArSSR model, the LR image and the HR image are represented using the same implicit neural voxel function with different sampling rates. Due to the continuity of the learned implicit function, a single ArSSR model is able to achieve arbitrary and infinite up-sampling rate reconstructions of HR images from any input LR image. Then the SR task is converted to approach the implicit voxel function via deep neural networks from a set of paired HR and LR training examples. The ArSSR model consists of an encoder network and a decoder network. Specifically, the convolutional encoder network is to extract feature maps from the LR input images and the fully-connected decoder network is to approximate the implicit voxel function. Experimental results on three datasets show that the ArSSR model can achieve state-of-the-art SR performance for 3D HR MR image reconstruction while using a single trained model to achieve arbitrary up-sampling scales. Code and data for this work are available at: https://github.com/iwuqing/ArSSR