A5026085823- Ultrasound Imaging and Elastography
- Ultrasound and Hyperthermia Applications
- Photoacoustic and Ultrasonic Imaging
- Liver Disease Diagnosis and Treatment
- Spectroscopy Techniques in Biomedical and Chemical Research
- ECG Monitoring and Analysis
- Ultrasonics and Acoustic Wave Propagation
- Radiomics and Machine Learning in Medical Imaging
- EEG and Brain-Computer Interfaces
- Medical Image Segmentation Techniques
- Blind Source Separation Techniques
- Cardiovascular Function and Risk Factors
- Non-Invasive Vital Sign Monitoring
- AI in cancer detection
- Cardiac Valve Diseases and Treatments
- Hepatocellular Carcinoma Treatment and Prognosis
- Advanced X-ray and CT Imaging
- Heart Rate Variability and Autonomic Control
- Liver Disease and Transplantation
- Infrared Thermography in Medicine
- Cardiovascular Disease and Adiposity
- Viral gastroenteritis research and epidemiology
- Thermography and Photoacoustic Techniques
- Domain Adaptation and Few-Shot Learning
- Soft Robotics and Applications
Beijing University of Technology
2016-2025
China International Science and Technology Cooperation
2021
Sichuan University
2007
Accurate segmentation of liver from abdominal CT scans is critical for computer-assisted diagnosis and therapy. Despite many years research, automatic remains a challenging task. In this paper, novel method was proposed delineation on volume images using supervoxel-based graph cuts. To extract the interest (VOI), region abdomen firstly determined based maximum intensity projection (MIP) thresholding methods. Then, patient-specific VOI extracted by histogram-based adaptive morphological...
Gas bubbles induced during the radiofrequency ablation (RFA) of tissues can affect detection zones (necrosis zone or thermal lesion) ultrasound elastography. To resolve this problem, our previous study proposed Nakagami imaging for detecting thermal-induced bubble formation to evaluate zones. prepare future applications, (i) created a novel algorithmic scheme based on frequency and temporal compounding enhanced visualization, (ii) integrated algorithm into clinical scanner develop real-time...
Three-dimensional (3D) liver tumor segmentation from Computed Tomography (CT) images is a prerequisite for computer-aided diagnosis, treatment planning, and monitoring of cancer. Despite many years research, 3D remains challenging task. In this paper, an efficient semiautomatic method was proposed in CT volumes based on improved fuzzy C -means (FCM) graph cuts. With single seed point, the volume interest (VOI) extracted using confidence connected region growing algorithm to reduce...
Computerized tumor segmentation on breast ultrasound (BUS) images remains a challenging task. In this paper, we proposed new method for semi-automatic BUS using Gaussian filtering, histogram equalization, mean shift, and graph cuts. The only interaction required was to select two diagonal points determine region of interest (ROI) an input image. ROI image shrunken by factor 2 bicubic interpolation reduce computation time. smoothed filter then contrast-enhanced equalization. Next, the...
In this paper we proposed a wearable electrocardiogram (ECG) telemonitoring system for atrial fibrillation (AF) detection based on smartphone and cloud computing. A ECG patch was designed to collect signals send the an Android via Bluetooth. An APP developed display waveforms in real time transmit every 30 s data remote server. machine learning (CatBoost)-based classification method detect AF case of detected AF, server pushed results web browser doctor. Finally, displayed doctor's diagnosis...
In this paper, a fetal electrocardiogram (ECG) monitoring system based on the Android smartphone was proposed. We designed portable low-power ECG collector, which collected maternal abdominal signals in real time. The data were sent to client via Bluetooth. Smartphone app software developed system. integrated fast fixed-point algorithm for independent component analysis (FastICA) and sample entropy algorithm, sake of real-time extraction from signals. heart rate computed using extracted...
Detecting atrial fibrillation (AF) from electrocardiogram (ECG) recordings remains a challenging task. In this paper, new AF detection method was proposed to classify the ECG into one of four classes: Normal rhythm, AF, Other and Noisy recordings.The comprised preprocessing, feature extraction, classification. R-peaks were detected, RR intervals delta extracted. 30 multi-level features extracted, including (n = 4), morphology 20), interval 2), similarity index between beats 4)....
Objective . The fast fixed-point algorithm for independent component analysis (FastICA) has been widely used in fetal electrocardiogram (ECG) extraction. However, the FastICA is sensitive to initial weight vector, which affects convergence of algorithm. In order solve this problem, an improved method was proposed extract ECG. Methods First, maternal abdominal mixed signal centralized and whitened, overrelaxation factor incorporated into Newton’s iterative process vector randomly generated....
Fetal electrocardiogram (FECG) signals directly reflect the electrical activity of fetal heart, enabling assessment cardiac health. To effectively separate and extract FECG from maternal abdominal (ECG) signals, this study proposed a W-shaped parallel network, termed Attention R2W-Net, which consisted two R2U-Nets. In encoder decoder, recurrent residual modules were used to replace feedforward convolutional layers, significantly enhancing feature representation improving noise suppression....
The analysis of the backscattered statistics using Nakagami parameter is an emerging ultrasound technique for assessing hepatic steatosis and fibrosis. Previous studies indicated that echo amplitude distribution a normal liver follows Rayleigh (the m close to 1). However, different frequencies may change livers. This study explored frequency dependence in human livers then discussed sources scattering liver. A total 30 healthy participants were enrolled undergo standard care examination on...
In this study, we proposed an intelligent health monitoring system based on smart clothing. The consisted of clothing and sensing component, care institution control platform, mobile device. is a wearable device for electrocardiography signal collection heart rate monitoring. integrated our fast empirical mode decomposition algorithm denoising hidden Markov model–based fall detection. Eight kinds services were provided by the system, including surveillance signs life, tracking physiological...
Hepatic steatosis is a key manifestation of non-alcoholic fatty liver disease (NAFLD). Early detection hepatic critical importance. Currently, biopsy the clinical golden standard for assessment. However, invasive and associated with sampling errors. Ultrasound has been recommended as first-line diagnostic test management NAFLD. B-mode ultrasound qualitative can be affected by factors including image post-processing parameters. Quantitative (QUS) aims to extract quantified acoustic parameters...