A5012276083- Advanced MRI Techniques and Applications
- Advanced NMR Techniques and Applications
- NMR spectroscopy and applications
- Medical Imaging Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Photoacoustic and Ultrasonic Imaging
- MRI in cancer diagnosis
- Atomic and Subatomic Physics Research
- Sparse and Compressive Sensing Techniques
- Electron Spin Resonance Studies
- Functional Brain Connectivity Studies
- Radiomics and Machine Learning in Medical Imaging
- Seismic Imaging and Inversion Techniques
- Lanthanide and Transition Metal Complexes
- Image and Signal Denoising Methods
- Advanced Image Processing Techniques
- Brain Tumor Detection and Classification
- Nuclear Physics and Applications
- Meningioma and schwannoma management
- Cardiac Imaging and Diagnostics
- Ultrasound Imaging and Elastography
- Image Processing Techniques and Applications
- Advanced X-ray Imaging Techniques
- Medical Image Segmentation Techniques
- Molecular spectroscopy and chirality
Xiamen University
2015-2025
Xiamen University of Technology
2018-2023
Resonance Research (United States)
2023
University of Rochester
2017
Deep learning (DL) has driven innovation in the field of computational imaging. One its bottlenecks is unavailable or insufficient training data. This article reviews an emerging paradigm, imaging physics-based data synthesis (IPADS), that can provide huge biomedical magnetic resonance (MR) without with few real Following physical law MR, IPADS generates signals from differential equations analytical solution models, making more scalable and explainable better protecting privacy. Key...
Reducing the acquisition time is important for clinical magnetic resonance imaging (MRI). Compressed sensing has recently emerged as a theoretical foundation reconstruction of images from undersampled k-space measurements, assuming those are sparse in certain transform domain. However, most real-world signals compressible rather than exactly sparse. For example, commonly used two-dimensional wavelet compressed MRI (CS-MRI) does not sparsely represent curves and edges. In this article, we...
Ferroptosis has been realized in anticancer drug–induced acute cardiac/kidney injuries (ACI/AKI); however, molecular imaging approach to detect ferroptosis ACI/AKI is a challenge. We report an artemisinin-based probe (Art-Gd) for contrast-enhanced magnetic resonance of (feMRI) by exploiting the redox-active Fe(II) as vivid chemical target. In vivo, Art-Gd showed great feasibility early diagnosis ACI/AKI, which was at least 24 and 48 hours earlier than standard clinical assays assessing ACI...
A synthetic method to prepare novel multifunctional core-shell-structured mesoporous silica nanoparticles for simultaneous magnetic resonance (MR) and fluorescence imaging, cell targeting photosensitization treatment has been developed. Superparamagnetic magnetite fluorescent dyes are co-encapsulated inside nonporous as the core provide dual-imaging capabilities (MR optical). The photosensitizer molecules, tetra-substituted carboxyl aluminum phthalocyanine (AlC4Pc), covalently linked shell...
Purpose An end‐to‐end deep convolutional neural network (CNN) based on residual (ResNet) was proposed to efficiently reconstruct reliable T 2 mapping from single‐shot overlapping‐echo detachment (OLED) planar imaging. Methods The training dataset obtained simulations that were carried out SPROM (Simulation with PRoduct Operator Matrix) software developed by our group. relationship between the original OLED image containing two echo signals and corresponding learned ResNet training. After...
The reconstruction of MR quantitative susceptibility mapping (QSM) from local phase measurements is an ill posed inverse problem and different regularization strategies incorporating a priori information extracted magnitude images have been proposed. However, the anatomy observed in does not always coincide spatially with that maps, which could give erroneous estimation reconstructed map. In this paper, we develop structural feature based collaborative (SFCR) method for QSM including both...
Background Conventional quantitative MRI (qMRI) scan is time‐consuming and highly sensitive to movements, posing great challenges for images of individuals with involuntary such as Huntington's disease (HD). Purpose To evaluate the potential our developed ultra‐fast qMRI technique, multiple overlapping‐echo detachment (MOLED), in overcoming head motion its capacity quantitatively assess tissue changes HD. Study Type Prospective. Phantom/Subjects A phantom comprising 13 tubes MnCl 2 at...
Abstract Objective: This study aims to address the challenge of domain discrepancies between synthetic and real data in quantitative MRI, particularly multi-parametric mapping using multiple overlapping-echo detachment (MOLED) imaging, which provides rapid versatile imaging for clinical applications.
 Approach: A adaptation method named MaskedUnet was proposed. Specifically, we employed a mask-based self-supervised pre-training model learn knowledge from unlabeled MOLED images....
Quantitative magnetic resonance imaging (qMRI) offers reliable biomarkers in clinic. Nevertheless, most qMRI methods are time-consuming and sensitive to motion. Single-shot multiple overlapping-echo detachment (MOLED) can deliver robust T2 mapping about 100 ms with high motion tolerance. However, its spatial resolution is relatively low due the limitations of signal-to-noise ratio (SNR) echo-train length. At mean time, number echoes different evolution times collected usually limited, which...
Fluid-attenuated inversion recovery (FLAIR) is indispensable in MRI-based head-and-neck assessments, but its quantitative counterpart remains clinically absent due to the influence of cerebrospinal fluid (CSF) dynamics and lengthy acquisition time spent on a series weighting-increasing images. This work implements validates fast fluid-attenuated T2 (FLA-T2) mapping via inversion-recovery-prepared multiple overlapping-echo detachment imaging (IR-MOLED). The clinical value prospectively...
Purpose To investigate the characteristics of nuclear Overhauser enhancement (NOE) imaging signals in brain at 7T. Methods Fresh hen eggs, as well six healthy, and C6 glioma‐bearing Wistar rats were scanned using chemical exchange saturation transfer‐magnetic resonance (CEST‐MRI) spectroscopy (CEST‐MRS) sequences (saturation duration 3 s, power 1.47 µT) with without lipid suppression. CEST data acquired over an offset range −6 to +6 ppm relative water 0.5 steps. Results The not disrupted by...
Abstract A novel image encoding approach based on linear frequency‐swept excitation has been recently proposed to overcome artifacts induced by various field perturbations in single‐shot echo planar imaging. In this article, we develop a new super‐resolved reconstruction method for it using the concepts of local k‐space and partial Fourier transform. This is superior originally developed conjugate gradient algorithm convenience, quality, stability solution. Reduced field‐of‐view applied...
Use of synthetic data has provided a potential solution for addressing unavailable or insufficient training samples in deep learning-based magnetic resonance imaging (MRI). However, the challenge brought by domain gap between and real is usually encountered, especially under complex experimental conditions. In this study, combining Bloch simulation general MRI models, we propose framework lack supervised learning scenarios, termed MOST-DL. A challenging application demonstrated to verify...
Quantitative magnetic resonance imaging (MRI) is of great value to both clinical diagnosis and scientific research. However, most MRI experiments remain qualitative, especially dynamic MRI, because repeated sampling with variable weighting parameter makes quantitative time-consuming sensitive motion artifacts. A single-shot T <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> mapping method based on multiple overlapping-echo acquisition...
Purpose Quantitative MRI (qMRI) is of great importance to clinical medicine and scientific research. However, most qMRI techniques are time‐consuming sensitive motion, especially when a large 3D volume imaged. To accelerate the acquisition, framework proposed realize reliable simultaneous multi‐slice T 2 mapping. Methods The mapping based on overlapping‐echo detachment (OLED) planar imaging (dubbed SMS‐OLED). Multi‐slice signals were generated by multiple excitation pulses together with...
To develop a deep learning-based method, dubbed Denoising CEST Network (DECENT), to fully exploit the spatiotemporal correlation prior image denoising.DECENT is composed of two parallel pathways with different convolution kernel sizes aiming extract global and spectral features embedded in images. Each pathway consists modified U-Net residual Encoder-Decoder network 3D convolution. Fusion 1 × utilized concatenate pathways, output DECENT noise-reduced The performance was validated numerical...