A5100654429- Advanced MRI Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Functional Brain Connectivity Studies
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Parkinson's Disease Mechanisms and Treatments
- Neurological disorders and treatments
- Medical Image Segmentation Techniques
- Medical Imaging and Analysis
- Advanced Image Processing Techniques
- Fetal and Pediatric Neurological Disorders
- Radiomics and Machine Learning in Medical Imaging
- Advanced Vision and Imaging
- Neonatal and fetal brain pathology
- Domain Adaptation and Few-Shot Learning
- Human Pose and Action Recognition
- Hand Gesture Recognition Systems
- Advancements in Battery Materials
- Photoacoustic and Ultrasonic Imaging
- MRI in cancer diagnosis
- Advanced Neural Network Applications
- Sparse and Compressive Sensing Techniques
- Image and Signal Denoising Methods
- Atomic and Subatomic Physics Research
- Brain Tumor Detection and Classification
ShanghaiTech University
2018-2025
Affiliated Hospital of Nantong University
2025
Nantong University
2025
Anhui University of Traditional Chinese Medicine
2025
Jilin Medical University
2024
Jilin University
2019-2024
Army Medical University
2023-2024
Xinqiao Hospital
2021-2024
Sichuan University
2024
State Key Laboratory of Oral Diseases
2024
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 generalization problem. Recently, Implicit Neural Representation (INR) has emerged as a powerful DL-based tool solving inverse problem by characterizing attributes signal continuous function corresponding...
Scene flow describes the motion of 3D objects in real world and potentially could be basis a good feature for action recognition. However, its use recognition, especially context convolutional neural networks (ConvNets), has not been previously studied. In this paper, we propose extraction scene recognition from RGB-D data. Previous works have considered depth RGB modalities as separate channels extract features later fusion. We take different approach consider one entity, thus allowing at...
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, patient cooperation ability, isotropic 3-dimensional (3D) HR image acquisition typically requests long time and, results in small spatial coverage low signal-to-noise ratio (SNR). Recent studies showed that, with deep convolutional neural networks, MR could be recovered from low-resolution...
The brain tissue phase contrast in MRI sequences reflects the spatial distributions of multiple substances, such as iron, myelin, calcium, and proteins. These substances with paramagnetic diamagnetic susceptibilities often colocalize one voxel regions. Both opposing play vital roles development neurodegenerative diseases. Conventional QSM methods only provide voxel-averaged susceptibility value cannot disentangle intravoxel opposite signs. Advanced imaging have been recently developed to...
Abstract Oceans/brine offers a massive supply of lithium sources that can support the renewable energy storage system. However, current extraction processes from seawater are complicated for scalable production. Here, high‐performance solar‐driven, direct lithium‐extraction felt (DEF) is developed. DEF consists reasonable addition Li 1.6 Mn O 4 particles on polypropylene/polyethylene core‐sheath fibers, which dark‐colored and float top bodies water. Compared with conventional method, shows...
Purpose To evaluate the magnetic susceptibility properties of different anatomical structures within knee joint using quantitative mapping (QSM). Methods A collagen tissue model was simulated and ex vivo animal cartilage experiments were conducted at 9.4 Tesla (T) to B 0 orientation‐dependent contrast observed in cartilage. Furthermore, nine volunteers (six healthy subjects without pain history three patients with known injury, between 29 58 years old) scanned gradient‐echo acquisitions on a...
Imaging markers sensitive to neurodegeneration in the substantia nigra are critically needed for future disease-modifying trials. Previous studies have demonstrated utility of posterior free water as a marker progression Parkinson's disease. In this study, we tested hypothesis that is elevated idiopathic REM sleep behaviour disorder, which considered prodromal stage synucleinopathy. We applied free-water imaging 32 healthy control subjects, 34 patients with disorder and 38 Eighteen subjects...
Emerging Metaverse applications demand reliable, accurate, and photorealistic reproductions of human hands to perform sophisticated operations as if in the physical world. While real hand represents one most intricate coordination between bones, muscle, tendon, skin, state-of-the-art techniques unanimously focus on modeling only skeleton hand. In this paper, we present NIMBLE, a novel parametric model that includes missing key components, bringing 3D new level realism. We first annotate...
In the present work, we propose a Self-supervised COordinate Projection nEtwork (SCOPE) to reconstruct artifacts-free CT image from single SV sinogram by solving inverse tomography imaging problem. Compared with recent related works that solve similar problems using implicit neural representation network (INR), our essential contribution is an effective and simple re-projection strategy pushes reconstruction quality over supervised deep learning works. The proposed inspired relationship...
Although antagonists of mineralocorticoid receptor (MR) have been widely used to treat heart failure, the underlying mechanisms are incompletely understood. Recent reports show that T cells play important roles in pathologic cardiac hypertrophy and failure. However, it is unclear whether how MR functions under these conditions. We found antagonist suppressed abdominal aortic constriction-induced decreased accumulation activation CD4+ CD8+ mouse heart. T-cell knockout mice manifested...
This paper addresses the problem of continuous gesture recognition from sequences depth maps using Convolutional Neural networks (ConvNets). The proposed method first segments individual gestures a sequence based on quantity movement (QOM). For each segmented gesture, an Improved Depth Motion Map (IDMM), which converts into one image, is constructed and fed to ConvNet for recognition. IDMM effectively encodes both spatial temporal information allows fine-tuning with existing models...
Quantitative susceptibility mapping (QSM) has demonstrated great potential in quantifying tissue various brain diseases. However, the intrinsic ill-posed inverse problem relating phase to underlying distribution affects accuracy for susceptibility. Recently, deep learning shown promising results improve by reducing streaking artifacts. there exists a mismatch between observed and theoretical forward estimated label. In this study, we proposed model-based architecture that followed STI...
This paper presents AlScN piezoelectric two-axis MEMS mirrors with gimbal-less and gimbaled designs fabricated in a CMOS-compatible manner. Integrated sensors provided feedback signals of the actual mirror positions. The diameter 1.5 mm possessed adjustable optical tilt angles up to 22.6° @ 30 V, high resonance frequency about 8.2 kHz, while 3 reached 48.5° 41 V. structure exhibited an excellent field view good mechanical decoupling. Additionally, significant improvement scanning performance...
Abstract Electrochemical lithium extraction from salt lakes using LiMn 2 O 4 (LMO) presents an eco‐friendly, highly controllable, and efficient method. However, its practical application is limited due to structure instability manganese dissolution in water. Herein, a high‐performance LMO coated with ≈3.5 nm thickness lithiated Nafion (Li‐Nafion) for electrochemical reported. The Li‐Nafion coating constructs fast lithium‐ion transport pathway enhances the hydrophilicity of particles,...