A5101489332- Prostate Cancer Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Medical Imaging and Analysis
- Radiation Dose and Imaging
- Spine and Intervertebral Disc Pathology
- Parallel Computing and Optimization Techniques
- Prostate Cancer Treatment and Research
- HVDC Systems and Fault Protection
- Cardiac Imaging and Diagnostics
- High-Voltage Power Transmission Systems
- Musculoskeletal pain and rehabilitation
- Advanced Data Storage Technologies
- Power Systems Fault Detection
- Interconnection Networks and Systems
- Cerebrovascular and Carotid Artery Diseases
- Distributed and Parallel Computing Systems
- Urologic and reproductive health conditions
- Autopsy Techniques and Outcomes
- Distributed systems and fault tolerance
- Advanced Optimization Algorithms Research
- Advanced Measurement and Detection Methods
- Blind Source Separation Techniques
- Renal cell carcinoma treatment
Xi'an Jiaotong University
2020-2024
Shanghai Electric (China)
2024
Peking University First Hospital
2015-2024
Peking University
2015-2024
Xinjiang University
2024
Ganzhou People's Hospital
2024
Tianjin University
2021
Xi'an Institute of Optics and Precision Mechanics
2015
Shenzhen Institutes of Advanced Technology
2014
81th Hospital of PLA
2012
Deep learning for diagnosing clinically significant prostate cancer (csPCa) is feasible but needs further evaluation in patients with prostate-specific antigen (PSA) levels of 4-10 ng/mL.To explore diffusion-weighted imaging (DWI), alone and combination T2-weighted (T2WI), deep-learning-based models to detect localize visible csPCa.Retrospective.One thousand six hundred twenty-eight systematic cognitive-targeted biopsy-confirmation (1007 csPCa, 621 non-csPCa) were divided into model...
Background Radiomics approaches based on multiparametric MRI (mp‐MRI) have shown high accuracy in prostate cancer (PCa) management. However, there is a need to apply radiomics the preoperative prediction of extracapsular extension (ECE). Purpose To develop and validate signature preoperatively predict probability ECE for patients with PCa, compared radiologists' interpretations. Study Type Retrospective. Population In total, 210 pathology‐confirmed status (101 positive, 109 negative) were...
Background Compressed sensing (CS) has been widely used to improve the speed of MRI, but feasibility application in 3D intracranial MR angiography (MRA) needs be evaluated clinical practice. Purpose To evaluate CS‐MRA comparison with conventional 3D‐MRA (Con‐MRA). Study Type Retrospective. Subjects Forty‐nine consecutive patients suspected arterial disease. Field Strength/Sequence 3T MRI. time‐of‐flight (TOF) MRA using a CS algorithm and TOF scan. Assessment Three radiologists (4, 11, 12...
Computer-aided diagnosis (CAD) systems have been proposed to assist radiologists in making diagnostic decisions by providing helpful information. As one of the most important sequences prostate magnetic resonance imaging (MRI), image features from T2-weighted images (T2WI) were extracted and evaluated for performances using CAD. We 12 quantitative MR images. The importance each feature cancer identification was compared peripheral zone (PZ) central gland (CG), respectively. performance...
Background Lower back pain is one of the most widely experienced health problems and strongly associated with intervertebral disc (IVD) degeneration. The quantification degeneration valuable for estimation material properties IVDs then to perform biomechanical simulation spinal conditions treatments. MR image characteristics relatively high intraclass variability small interclass differences pose challenges classification algorithm automatic grading degenerated IVD. Purpose To assess...
Artificial intelligence (AI) assistance may enhance radiologists' performance in detecting clinically significant prostate cancer (csPCa) on MRI. Further validation is needed for radiologists with different experiences.
To investigate the biochemical changes in lumbar facet joint (LFJ) and intervertebral disc (IVD) with different degenerative grade by T2* mapping.
Parallel computing performance on scalable shared-memory architectures is affected by the structure of interconnection networks linking processors to memory modules and efficiency memory/cache management systems. Cache Coherence Nonuniform Memory Access (CC-NUMA) Only (COMA) are two effective systems, hierarchical ring an efficient network in hardware. This paper focuses comparative modeling evaluation CC-NUMA COMA a architecture. Analytical models for systems presented. Intensive...
This paper presents a content based modified reaction diffusion (RD) equation for modeling glioma growth. The is by weighted parameter that measures the white matter proportion in small window. Given two MRI time-points scans of same patient, manually segmented tumor first scan used as an initial seed to proposed method while second ground truth measure accuracy simulated results. For healthy tissues segmentation around seed, spatial fuzzy C-means algorithm accounts neighborhood information...
Electromyography (EMG) signal is one of biological signals, it has been used in rehabilitation and prosthesis for several decades. For the control prosthetic hands, EMG signals are usually to make classification recognize hand gestures or wrist motion patterns, but most research neglect continuous wrist, as a result, those hands can't move continuously user's intention. In this study, we proposed novel method based on long short-term memory (LSTM) predict joint torque from signal. Five...
<title>Abstract</title> Three-terminal hybrid DC transmission technology has the advantages of long-distance and large capacity, there is no phase change failure other problems, which an effective means sending out new energy bases. Correspondingly, reliability existing single-ended traveling wave protection further degraded by unknown fault characteristics introduced greater variety combination converters add-ons in three-terminal system. Therefore, a scheme based on refractive coefficient...
Gearboxes play a vital role in the power transmission of mechanical equipment, and studying fault diagnosis methods is essential to ensure normal operation rotating machines. Since vibration signal gearbox has unstable characteristics with strong background noise, novel approach for wind turbine based on variational mode decomposition (VMD) optimized by sparrow search algorithm (SSA) improved refined composite multi-scale dispersion entropy (IRCMDE) proposed this paper. Firstly, reducing...
Abstract Three-terminal hybrid DC transmission technology has the advantages of long-distance and large capacity, there is no phase change failure other problems, which an effective means sending out new energy bases. Correspondingly, reliability existing single-ended traveling wave protection further degraded by unknown fault characteristics introduced greater variety combination converters add-ons in three-terminal system. Therefore, a scheme based on refractive coefficient proposed....
The basic working principle of single-ring absolute photoelectric shaft encoder is to use light-emitting diode as light source illuminate the encoder, at same time using linear CCD signal receiving device and subdivision device. So essence single ring technology based on line array technology. This paper proposes a algorithm Based polynomial interpolation method. By computing center bar code get value accurate positioning, this calculates coded disc line. As result existence encoder's...
Objective To investigate image quality and radiation dose of prospective ECG-gated coronary combined with carotid cerebrovascular angiography compare it common CTA carotid-cerebrovascular at a 256-slice spiral CT.Methods Fifty-seven patients were included in the study.The data was analyzed retrospectively divided into 3 groups.Group 1 underwent ( n =17 ),which wide range coronary,carotid cerebral vascular one-stop angiography.Group 2 =20),which routine (n =20).Mean CT attenuation noise...
The snapshot hyperspectral imaging is an emerging technique with numerous applications. However, the reconstruction often time-consuming, which placing a limit on development of imaging. We present efficient algorithm based tensor analysis and low-rank constraint. data cube regarded as low rank three-order tensor, can jointly treat both spatial spectral modes. 3D-LRC method greatly decrease computation time without unfolding into 2D patches. Compared the-state-of-the-art method, proposed has...
This paper presents a multiprocessor performance prediction methodology supported by experimental measurements, which predicts the execution time of large application programs on parallel architectures based small set sample data. We propose graph model to describe program behavior. Important and implicit architecture parameters are obtained experiments. focus predictions multiprocessors with communications. A scientific simulation is implemented using shared-memory KSR-1 data-parallel CM-5...