Xinlin Zhang

Xinlin Zhang

Auto-generated profile, based on publicly available information

Xinlin Zhang

Fuzhou University

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 April 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
XZXinlin Zhang
Xinlin Zhang
HLHengfa Lu
Hengfa Lu
DGDi Guo
Di Guo
ZLZongying Lai
Zongying Lai
HYHuihui Ye
Huihui Ye
XQXiaobo Qu
Xiaobo Qu
Magnetic resonance imaging serves as an essential tool for clinical diagnosis, however, suffers from a long acquisition time. Sparse sampling effectively saves this time but images need to be faithfully reconstructed from undersampled data. Among the existing reconstruction methods, the structured low-rank methods have advantages in robustness to the sampling patterns and lower error. However, the structured low-rank methods use the 2D or higher dimension k-space data to build a huge block Hankel matrix, leading to considerable time and memory consumption. To reduce the size of the Hankel matrix, we proposed to separably construct multiple small Hankel matrices from rows and columns of the k-space and then constrain the low-rankness on these small matrices. This separable model can significantly reduce the computational time but ignores the correlation existed in inter- and intra-row or column, resulting in increased reconstruction error. To improve the reconstructed image without obviously increasing the computation, we further introduced the self-consistency of k-space and virtual coil prior. Besides, the proposed separable model can be extended into other imaging scenarios which hold exponential characteristics in the parameter dimension. The in vivo experimental results demonstrated that the proposed method permits the lowest reconstruction error with a fast reconstruction. The proposed approach requires only 4% of the state-of-the-art STDLR-SPIRiT runtime for parallel imaging reconstruction, and achieves the fastest computational speed in parameter imaging reconstruction.

20 June 2023 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
CQChen Qian
Chen Qian
ZWZi Wang
Zi Wang
XZXinlin Zhang
Xinlin Zhang
BSBoxuan Shi
Boxuan Shi
BJBoyu Jiang
Boyu Jiang
XQXiaobo Qu
Xiaobo Qu
Objective : Multi-shot interleaved echo planer imaging (Ms-iEPI) can obtain diffusion-weighted images (DWI) with high spatial resolution and low distortion, but suffers from ghost artifacts introduced by phase variations between shots. In this work, we aim at solving the ms-iEPI DWI reconstructions under inter-shot motions and ultra-high b-values. Methods : An iteratively joint estimation model with paired phase and magnitude priors is proposed to regularize the reconstruction (PAIR). The former prior is low-rankness in the k-space domain. The latter explores similar edges among multi-b-value and multi-direction DWI with weighted total variation in the image domain. The weighted total variation transfers edge information from the high SNR images (b-value = 0) to DWI reconstructions, achieving simultaneously noise suppression and image edges preservation. Results : Results on simulated and in vivo data show that PAIR can remove inter-shot motion artifacts very well (8 shots) and suppress the noise under the ultra-high b-value (4000 s/mm 2 ) significantly. Conclusion : The joint estimation model PAIR with complementary priors has a good performance on challenging reconstructions under inter-shot motions and a low signal-to-noise ratio. Significance : PAIR has potential in advanced clinical DWI applications and microstructure research.

18 March 2025 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
TWTao Wang
Tao Wang
XZXinlin Zhang
Xinlin Zhang
YZYuanbo Zhou
Yuanbo Zhou
YCYuanbin Chen
Yuanbin Chen
LZLongxuan Zhao
Longxuan Zhao
TTTong Tong
Tong Tong
In recent years, supervised learning using convolutional neural networks (CNN) has served as a benchmark for various medical image segmentation and classification. However, supervised learning deeply relies on large-scale annotated data, which is expensive, time-consuming, and even impractical to acquire in medical imaging applications. Moreover, effective utilization of annotation resources might not always be feasible during the annotation process. To optimize the utilization of annotation resources, a proposed active learning framework is introduced that is applicable to both 2D and 3D segmentation and classification tasks. This framework aims to reduce annotation costs by selecting more valuable samples for annotation from the pool of unlabeled data. Based on the perturbation consistency, we apply different perturbations to the input data and propose a perturbation consistency evaluation module to evaluate the consistency among predictions when applying different perturbations to the data. Subsequently, we rank the consistency of each data and select samples with lower consistency as high-value candidates. These selected samples are prioritized for annotation. We extensively validated our proposed framework on three publicly available and challenging medical image datasets, Kvasir Dataset, COVID-19 Infection Segmentation Dataset, and BraTS2019 Dataset. The experimental results demonstrate that our proposed framework can achieve significantly improved performance with fewer annotations in 2D classification and segmentation and 3D segmentation tasks. The proposed framework enables more efficient utilization of annotation resources by annotating more representative samples, thus enhancing the model's robustness with fewer annotation costs.

27 January 2025 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
YHYiman Huang
Yiman Huang
SQShuxian Qu
Shuxian Qu
YXYushu Xie
Yushu Xie
HWHanlei Wang
Hanlei Wang
XZXinlin Zhang
Xinlin Zhang
XZXiaotong Zhang
Xiaotong Zhang
Objective: For low-field magnetic resonance imaging (MRI) in unshielded environment, existing methods have been proposed to eliminate electromagnetic interference (EMI) noise in each single radio-frequency (RF) receive coil. In the present study, we propose to use the EMI information from multiple MRI receive coils collectively in EMI denoising. Methods: The proposed method leverages the information of inter-channel correlation, including EMI detectors and RF receive coils to remove EMI noise. Calibration signals from both EMI detectors and RF receivers are concatenated to determine a de-correlation matrix, which is then used to denoise MRI signals. Results: Saline phantom and in vivo experiments demonstrated the efficacy of the proposed method in EMI elimination, showing that the proposed method outperformed advanced EMI elimination methods with up to 16.34% improvement in EMI noise removal percentage (NRP) and 1.58dB improvement in signal-to-noise ratio (SNR), along with reduced computational time. Conclusion: The proposed method effectively removes EMI noise and shows improved performance by using information from all receive coils. Significance: This method allows for the design of multi-receive coils for low-field MRI such as phased-arrays, which have the potential to enhance the performance in noise removal and improve the SNR in MRI signal acquisition.

25 January 2025 in Neurocomputing
Verified
Journal Article
Closed access
XQXintao Qiu
Xintao Qiu
YZYuanbo Zhou
Yuanbo Zhou
XZXinlin Zhang
Xinlin Zhang
YXYuyang Xue
Yuyang Xue
XLXiaoyong Lin
Xiaoyong Lin
QGQinquan Gao
Qinquan Gao