JFJie Feng

Jie Feng

*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


Jie Feng has a total of 64 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    MINeR: Direction-modulated implicit neural representation enables ultrafast multi-shell diffusion MRI

    by Tian Zeng, Jie Feng, Tong Sun, Guoyan Lao, Ming Zhang, Longchun Wang, Jingquan Liu, Yuyao Zhang, Hongjiang Wei


  • 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.


  • A subject-specific unsupervised deep learning method for quantitative susceptibility mapping using implicit neural representation

    by Ming Zhang, Ruimin Feng, Zhenghao Li, Jie Feng, Qing Wu, Zhiyong Zhang, Chengxin Ma, Jinsong Wu, Fuhua Yan, Chunlei Liu, et al.


  • 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.


  • Brain Age Prediction Based on Quantitative Susceptibility Mapping Using the Segmentation Transformer

    by Mingxing Chen, Yiqing Wang, Yuting Shi, Jie Feng, Ruimin Feng, Xiaojun Guan, Xiaojun Xu, Yuyao Zhang, Cheng Jin, Hongjiang Wei

    The process of brain aging is intricate, encompassing significant structural and functional changes, including myelination and iron deposition in the brain. Brain age could act as a quantitative marker to evaluate the degree of the individual's brain evolution. Quantitative susceptibility mapping (QSM) is sensitive to variations in magnetically responsive substances such as iron and myelin, making it a favorable tool for estimating brain age. In this study, we introduce an innovative 3D convolutional network named Segmentation-Transformer-Age-Network (STAN) to predict brain age based on QSM data. STAN employs a two-stage network architecture. The first-stage network learns to extract informative features from the QSM data through segmentation training, while the second-stage network predicts brain age by integrating the global and local features. We collected QSM images from 712 healthy participants, with 548 for training and 164 for testing. The results demonstrate that the proposed method achieved a high accuracy brain age prediction with a mean absolute error (MAE) of 4.124 years and a coefficient of determination (R 2 ) of 0.933. Furthermore, the gaps between the predicted brain age and the chronological age of Parkinson's disease patients were significantly higher than those of healthy subjects (P<0.01). We thus believe that using QSM-based predicted brain age offers a more reliable and accurate phenotype, with the potentiality to serve as a biomarker to explore the process of advanced brain aging.


  • Top Cited Papers
    Open Access

    APART-QSM: An improved sub-voxel quantitative susceptibility mapping for susceptibility source separation using an iterative data fitting method

    by Zhenghao Li, Ruimin Feng, Qiangqiang Liu, Jie Feng, Guoyan Lao, Ming Zhang, Jun Li, Yuyao Zhang, Hongjiang Wei


  • Open Access

    Full Scale-Aware Balanced High-Resolution Network for Multi-Person Pose Estimation

    by Shaohua Li, Haixiang Zhang, Hanjie Ma, Jie Feng, Mingfeng Jiang

    Scale variation is a major challenge in multi-person pose estimation. In scenes where persons are present at various distances, models tend to perform better on larger-scale persons, while the performance for smaller-scale persons often falls short of expectations. Therefore, effectively balancing the persons of different scales poses a significant challenge. So this paper proposes a new multi-person pose estimation model called FSA Net to improve the model’s performance in complex scenes. Our model utilizes High-Resolution Network (HRNet) as the backbone and feeds the outputs of the last stage’s four branches into the DCB module. The dilated convolution-based (DCB) module employs a parallel structure that incorporates dilated convolutions with different rates to expand the receptive field of each branch. Subsequently, the attention operation-based (AOB) module performs attention operations at both branch and channel levels to enhance high-frequency features and reduce the influence of noise. Finally, predictions are made using the heatmap representation. The model can recognize images with diverse scales and more complex semantic information. Experimental results demonstrate that FSA Net achieves competitive results on the MSCOCO and MPII datasets, validating the effectiveness of our proposed approach.


  • Open Access

    Imaging Insights of Isolated Idiopathic Dystonia: Voxel-Based Morphometry and Activation Likelihood Estimation Studies

    by Yunhao Wu, Chao Zhang, Yufei Li, Jie Feng, Ming Zhang, Hongxia Li, Tao Wang, Yingying Zhang, Zhijia Jin, Chencheng Zhang, et al.

    The understanding of brain structural abnormalities across different clinical forms of dystonia and their contribution to clinical characteristics remains unclear. The objective of this study is to investigate shared and specific gray matter volume (GMV) abnormalities in various forms of isolated idiopathic dystonia. We collected imaging data from 73 isolated idiopathic dystonia patients and matched them with healthy controls to explore the GMV alterations in patients and their correlations with clinical characteristics using the voxel-based morphometry (VBM) technique. In addition, we conducted an activation likelihood estimation (ALE) meta-analysis of previous VBM studies. Our study demonstrated widespread morphometry alterations in patients with idiopathic dystonia. Multiple systems were affected, which mainly included basal ganglia, sensorimotor, executive control, and visual networks. As the result of the ALE meta-analysis, a convergent cluster with increased GMV was found in the left globus pallidus. In subgroup VBM analyses, decreased putamen GMV was observed in all clinic forms, while the increased GMV was observed in parahippocampal, lingual, and temporal gyrus. GD demonstrated the most extensive GMV abnormalities in cortical regions, and the aberrant GMV of the posterior cerebellar lobe was prominent in CD. Moreover, trends of increased GMV regions of the left precuneus and right superior frontal gyrus were demonstrated in the moderate-outcome group compared with the superior-outcome group. Results of our study indicated shared pathophysiology of the disease-centered on the dysfunction of the basal ganglia-thalamo-cortical circuit, impairing sensorimotor integration, high-level motor execution, and cognition of patients. Dysfunction of the cerebello-thalamo-cortical circuit could also be involved in CD especially. Finally, the frontal-parietal pathway may act as a potential marker for predicting treatment outcomes such as deep brain stimulation.


  • Open Access

    A SVBRDF Modeling Pipeline using Pixel Clustering

    by Bo Li, Jie Feng, Bingfeng Zhou

    We present a pipeline for modeling spatially varying BRDFs (svBRDFs) of planar materials which only requires a mobile phone for data acquisition. With a minimum of two photos under the ambient and point light source, our pipeline produces svBRDF parameters, a normal map and a tangent map for the material sample. The BRDF fitting is achieved via a pixel clustering strategy and an optimization based scheme. Our method is light-weight, easy-to-use and capable of producing high-quality BRDF textures.