A5021953784- Medical Image Segmentation Techniques
- EEG and Brain-Computer Interfaces
- Radiomics and Machine Learning in Medical Imaging
- Functional Brain Connectivity Studies
- Brain Tumor Detection and Classification
- Advanced Neural Network Applications
- Medical Imaging Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Parkinson's Disease Mechanisms and Treatments
- AI in cancer detection
- Advanced MRI Techniques and Applications
- Neonatal and fetal brain pathology
- Medical Imaging and Analysis
- Robotics and Sensor-Based Localization
- 3D Shape Modeling and Analysis
- Neural dynamics and brain function
- Computer Graphics and Visualization Techniques
- Advanced Radiotherapy Techniques
- Cerebrovascular and Carotid Artery Diseases
- Fetal and Pediatric Neurological Disorders
- ECG Monitoring and Analysis
- MRI in cancer diagnosis
- Blind Source Separation Techniques
- Retinal Imaging and Analysis
Suzhou Institute of Biomedical Engineering and Technology
2016-2025
Chinese Academy of Sciences
2016-2025
University of Science and Technology of China
2021-2025
Xuzhou Medical College
2022-2024
Suzhou University of Science and Technology
2024
Harbin University of Science and Technology
2024
Huashan Hospital
2022
Fudan University
2022
Changchun University of Science and Technology
2022
University of North Carolina at Chapel Hill
2012-2013
Abstract Injectable hydrogel adhesives integrating both rapid adhesion to wet tissues and anti‐swelling in humid environments are highly desired for fast hemostasis wound sealing surgical applications. Herein, utilizing the synergistic effect of thermo‐sensitive shrinkable nano‐micelle gelators small molecular adhesive moieties, an injectable with rapid‐adhesion properties (RAAS hydrogel) is fabricated. The RAAS can undergo ultrafast gelation achieve within 2 s ultraviolet illumination...
Due to the unpredictable location, fuzzy texture, and diverse shape, accurate segmentation of kidney tumor in CT images is an important yet challenging task. To this end, we, paper, present a cascaded trainable model termed as Crossbar-Net. Our method combines two novel schemes: 1) we originally proposed crossbar patches, which consists orthogonal non-squared patches (i.e., vertical patch horizontal patch). The are able capture both global local appearance information tumors from directions...
The classification of motor imagery-electroen-cephalogram( MI-EEG)based brain-computer interface(BCI) can be used to decode neurological activities, which has been widely applied in the control external devices. However, two factors still hinder improvement accuracy and robustness, especially multi-class tasks. First, existing algorithms are based on a single space (measuring or source space). They suffer from holistic low spatial resolution measuring locally high information accessed space,...
Three dimension Computed Tomography (CT) reconstruction is computationally demanding. To accelerate the speed of reconstruction, Application Specific Integrated Circuit (ASIC) or Field Programmable Gate Array (FPGA) has been used, but they are expensive, inflexible and not easy to upgrade. The modern Graphics Processing Unit (GPU) with its programmable features improves this situation becomes one powerful flexible tools for 3D CT reconstruction. In paper, we implement Feldkamp-Davis-Kress...
The neuroimaging-based computer-aided diagnosis for Parkinson's disease (PD) has attracted considerable attention in recent years, where the classifier plays a critical role. Random vector functional link network (RVFL) shown its effectiveness classification task, while extended version, namely RVFL plus (RVFL+), integrates additional privileged information (PI) about training samples to help more effective classifier. On other hand, it is still popular way adopt only single neuroimaging...
The Student's-t mixture model, which is heavily tailed and more robust than the Gaussian has recently received great attention on image processing. In this paper, we propose a non-rigid point set registration algorithm using model. Specifically, first, consider alignment of two sets as probability density estimation problem treat one model centroids. Then, fit centroids to other treated data. Finally, get closed-form solutions parameters, leading computationally efficient algorithm. proposed...
Abstract Objective Impairment of basal ganglia (BG)‐thalamo‐cortical circuit causes various symptoms Parkinson's disease (PD). We investigated the functional connectivity (FC) patterns putamen among PD subtypes and healthy control (HC) explored their clinical significance. Methods A total 16 patients with tremor‐dominant (TD) PD, 23 postural instability gait difficulty‐dominant (PIGD) 31 HC that underwent magnetic resonance imaging were observed. Voxel‐wise FC analysis was performed by...
The design of software platform for medical imaging application has been increasingly prioritized as the sophisticated imaging. With this demand, we have designed and implemented a novel in traditional object-oriented fashion with some common patterns. This integrates mainstream algorithms image processing analyzing within consistent framework, including reconstruction, segmentation, registration, visualization, etc., provides powerful tool both scientists engineers. overall framework...
To compare the performance of radiomics to that Prostate Imaging Reporting and Data System (PI-RADS) v2.1 scoring system in detection clinically significant prostate cancer (csPCa) based on biparametric magnetic resonance imaging (bpMRI) vs. multiparametric MRI (mpMRI).A total 204 patients with pathological results were enrolled between January 2018 December 2019, 142 training cohort 62 testing cohort. The model was compared PI-RADS for diagnosis csPCa bpMRI mpMRI by using receiver operating...
Objective To develop and validate a radiomics nomogram that could incorporate clinicopathological characteristics ultrasound (US)-based signature to non-invasively predict Ki-67 expression level in patients with breast cancer (BC) preoperatively. Methods A total of 328 lesions from 324 BC who were pathologically confirmed our hospital June 2019 October 2020 included, they divided into high group low group. Routine US shear wave elastography (SWE) performed for each lesion, the ipsilateral...
Motor imagery-based brain-computer interfaces (MI-BCIs) hold significant promise for upper limb rehabilitation in stroke patients. However, traditional MI paradigm primarily involves various limbs and fails to effectively address unilateral needs. In addition, compared decoding MI-EEG signals from different limbs, same faces more challenges. We introduced a novel tri-class fine motor imagery (FMI) collected electroencephalogram (EEG) data 20 healthy subjects research. Furthermore, we...