A5072850055- Advanced Neuroimaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Fetal and Pediatric Neurological Disorders
- MRI in cancer diagnosis
- Parkinson's Disease Mechanisms and Treatments
- Functional Brain Connectivity Studies
- Neurological disorders and treatments
- Domain Adaptation and Few-Shot Learning
- Bone and Joint Diseases
- Multimodal Machine Learning Applications
- Optical Imaging and Spectroscopy Techniques
- Voice and Speech Disorders
- Machine Learning in Materials Science
- Remote Sensing and Land Use
- Ocular and Laser Science Research
- Salivary Gland Tumors Diagnosis and Treatment
- Advanced Statistical Process Monitoring
- Face Recognition and Perception
- Industrial Vision Systems and Defect Detection
- Medical Imaging and Analysis
- Advanced Control Systems Optimization
- Fault Detection and Control Systems
- Glaucoma and retinal disorders
- Sparse and Compressive Sensing Techniques
- Cancer-related molecular mechanisms research
Zhejiang University of Technology
2016-2024
Zhejiang Lab
2024
Brigham and Women's Hospital
2020-2023
Harvard University
2020-2023
Huawei Technologies (United Kingdom)
2021
Jilin University
2018
Shanghai University
2006
Language and theory of mind (ToM) are the cognitive capacities that allow for successful interpretation expression meaning. While functional MRI investigations able to consistently localize language ToM specific cortical regions, diffusion point an inconsistent sometimes overlapping set white matter tracts associated with these two domains. To further examine may underlie domains, we use a two-tensor tractography method investigate microstructure 809 participants from Human Connectome...
Abstract The retinogeniculate visual pathway (RGVP) conveys information from the retina to lateral geniculate nucleus. RGVP has four subdivisions, including two decussating and nondecussating pathways that cannot be identified on conventional structural magnetic resonance imaging (MRI). Diffusion MRI tractography potential trace these subdivisions is increasingly used study RGVP. However, it not yet known which fiber tracking strategy most suitable for reconstruction. In this study, methods...
Most existing domain adaptation methods focus on from only one source domain, however, in practice there are a number of relevant sources that could be leveraged to help improve performance target domain. We propose novel approach named T-SVDNet address the task Multi-source Domain Adaptation (MDA), which is featured by incorporating Tensor Singular Value Decomposition (T-SVD) into neural network's training pipeline. Overall, high-order correlations among multiple domains and categories...
Abstract The corticospinal tract (CST) is a critically important white matter fiber in the human brain that enables control of voluntary movements body. CST exhibits somatotopic organization, which means motor neurons specific body parts are arranged order within CST. Diffusion magnetic resonance imaging (MRI) tractography increasingly used to study anatomy However, despite many advances algorithms over past decade, modern, state‐of‐the‐art methods still face challenges. In this study, we...
Diffusion magnetic resonance imaging white matter tractography, an increasingly popular preoperative planning modality used for pre-surgical in brain tumor patients, is employed with the goal of maximizing resection while sparing postoperative neurological function. Clinical translation tractography has been limited by several shortcomings standard diffusion tensor (DTI), including poor modeling fibers crossing through regions peritumoral edema and low spatial resolution typical clinical MRI...
The retinogeniculate visual pathway (RGVP) plays an important role in the system. Diffusion MRI-based tractography has been successfully used to identify RGVP. However, challenges of RGVP remain because its highly curved path and intricate anatomical environment. One key is large false-positive fibers generated from that requires labor costs hand-draw ROIs for fiber filtering. Therefore, we presented a pipeline enable automated identification dMRI tractography. First, tractography-based...
The retinogeniculate pathway (RGVP) is responsible for carrying visual information from the retina to lateral geniculate nucleus. Identification and visualization of RGVP are important in studying anatomy system can inform treatment related brain diseases. Diffusion MRI (dMRI) tractography an advanced imaging method that uniquely enables vivo mapping 3D trajectory RGVP. Currently, identification data relies on expert (manual) selection streamlines, which time-consuming, has high clinical...
The segmentation of the retinogeniculate visual pathway (RGVP) is a significant quantitative tool for analyzing anatomy and trajectory individual RGVP. However, due to complex structure elongated morphology RGVP, it difficult accurately identify intracranial course based on single structural MRI or diffusion MRI. In this work, we propose novel deep multimodal fusion network segmentation, which fuses useful information from different modalities. Specifically, proposed model uses supervised...
Small size and intricate anatomical environment are the main difficulties facing tractography of facial–vestibulocochlear nerve complex (FVN), lead to challenges in fiber orientation distribution (FOD) modeling, tracking, region‐of‐interest selection, filtering. Experts need rich experience anatomy tractography, as well substantial labor costs, identify FVN. Thus, we present a pipeline FVN automatically, what believe is first study automated identification First, created an template. Forty...
Abstract The oculomotor nerve (OCN) is the main motor innervating eye muscles and can be involved in multiple flammatory, compressive, or pathologies. diffusion magnetic resonance imaging (dMRI) tractography now widely used to describe trajectory of OCN. However, complex cranial structure leads difficulties fiber orientation distribution (FOD) modeling, tracking, region interest (ROI) selection. Currently, identification OCN relies on expert manual operation, resulting challenges, such as...
The human visual pathway starts from the retina, passes through retinogeniculate pathway, optic radiation, and finally connects to primary cortex. Diffusion MRI tractography is only technology that can noninvasively reconstruct pathway. However, complete accurate reconstruction challenging because of skull base environment complex fiber geometries. Specifically, nerve within cause abnormal diffusion signals. crossing fanning fibers at chiasm, a sharp turn Meyer's loop contribute geometries A...
Fiber orientation distribution (FOD) estimation with diffusion magnetic resonance imaging (dMRI) is critical in white matter fiber tractography which most commonly implemented by tracking the principal direction of FOD step step. Ambiguous spatial correspondences between estimated directions and geometry, such as crossing, fanning or bending, makes challenging. As a consequence, lot tracts suggest intertangled connections unexpected regions actually stop prematurely matter. In this work, we...
Purpose: Fiber tracking with diffusion weighted magnetic resonance imaging has become an essential tool for estimating in vivo brain white matter architecture. results are sensitive to the choice of processing method and criteria. Phantom studies provide concrete quantitative comparisons methods relative absolute ground truths, yet do not capture variabilities because physiological factors. Methods: To date, a large-scale reproducibility analysis been performed assessment newest generation...
Streamline tractography locally traces peak directions extracted from fiber orientation distribution (FOD) functions, lacking global information about the trend of whole bundle. Therefore, it is prone to producing erroneous tracks while missing true positive connections. In this work, we propose a new bundle-specific (BST) method based on tractogram (BTD) function, which directly reconstructs trajectory start region termination by incorporating in bundle mask. A unified framework for any...
ABSTRACT The retinogeniculate visual pathway (RGVP) is responsible for carrying information from the retina to lateral geniculate nucleus. Identification and visualization of RGVP are important in studying anatomy system can inform treatment related brain diseases. Diffusion MRI (dMRI) tractography an advanced imaging method that uniquely enables vivo mapping 3D trajectory RGVP. Currently, identification data relies on expert (manual) selection streamlines, which time‐consuming, has high...
Motivation: The investigation of superficial white matter (SWM) poses challenges due to its small size, variability, delicate structure, high curvature, and fiber crossings in diffusion MRI tractography. Goal(s): Our goal is develop an innovative methodology for classifying SWM streamline clusters using tractography, leveraging brain-inspired learning-based techniques. Approach: A dual-phase method with Spiking Neural Networks (SNNs) leaky integrate fire (LIF) neurons developed the...
Diffusion magnetic resonance imaging (dMRI) provides critical insights into the microstructural and connectional organization of human brain. However, availability high-field, open-access datasets that include raw k-space data for advanced research remains limited. To address this gap, we introduce Diff5T, a first comprehensive 5.0 Tesla diffusion MRI dataset focusing on This includes reconstructed images, acquired using variety protocols. Diff5T is designed to support development...
Complex repairable systems with bathtub-shaped failure intensity will normally go through three periods in the lifecycle, which requires maintenance policies and management decisions accordingly.Therefore, accurate estimation of change points different has great significance.This paper addresses challenge change-point processes for systems, especially sustained gradual change.The proposes a sectional model composed two non-homogeneous Poisson (NHPPs) to describe intensity.In order obtain...