A5032865037- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Spectroscopy and Chemometric Analyses
- Remote-Sensing Image Classification
- Obstructive Sleep Apnea Research
- Spectroscopy Techniques in Biomedical and Chemical Research
- Thyroid Cancer Diagnosis and Treatment
- Lung Cancer Diagnosis and Treatment
- Image and Signal Denoising Methods
- Phonocardiography and Auscultation Techniques
- Medical Imaging and Analysis
- Advanced Image Processing Techniques
- Orthopedic Surgery and Rehabilitation
- Industrial Vision Systems and Defect Detection
- Foot and Ankle Surgery
- COVID-19 diagnosis using AI
- Non-Invasive Vital Sign Monitoring
- Advanced Image Fusion Techniques
- Bone fractures and treatments
- Optical Imaging and Spectroscopy Techniques
- Thyroid and Parathyroid Surgery
- Autopsy Techniques and Outcomes
- Cardiovascular and Diving-Related Complications
- Berberine and alkaloids research
- Optical Polarization and Ellipsometry
Tianjin University
2017-2025
Tianjin Hospital
2022
State Key Laboratory of Gas Disaster Detecting, Preventing and Emergency Controlling
2022
Berberine (BBR) has a neuroprotective effect against ischemic stroke, but its specific protective mechanism not been clearly elaborated. This study explored the of BBR on canopy FGF signaling regulator 2 (CNPY2) pathway in penumbra rats. The model cerebral ischemia-reperfusion injury (CIRI) was established by thread embolization method, and gastrically perfused for 48 h or 24 before operation 6 after operation. rats were randomly divided into four groups: Sham group, CIRI + group. After...
Accurate segmentation and recognition algorithm of lung nodules has great important value reference for early diagnosis cancer. An is proposed 3D CT sequence images in this paper based on Res U-Net network ResNet50 classification network. The common convolutional layers encoding decoding paths are replaced by residual units while the loss function changed to Dice after using cross entropy accelerate convergence. Since small rich information, improved replacing 2D with reducing sizes some...
Colposcopy is an important method in the diagnosis of cervical lesions. However, experienced colposcopists are lacking at present, and training cycle long. Therefore, artificial intelligence-based colposcopy-assisted examination has great prospects. In this paper, a lesion segmentation model (CLS-Model) was proposed for region from colposcopic post-acetic-acid images accurate results could provide good foundation further research on classification selection biopsy site.First, improved Faster...
Abstract Coronary vessel segmentation plays a pivotal role in automating the auxiliary diagnosis of coronary heart disease. The continuity and boundary accuracy segmented vessels directly affect subsequent processing. Notably, during segmentation, with severe stenosis can easily cause errors breakage, resulting isolated islands. To address these issues, we propose novel multi-scale U-shaped transformer aggregation topology preservation (UT-BTNet) for angiography. Specifically, considering...
Background Early diagnosis of non-union fractures is vital for treatment planning, yet studies using bone morphometric parameters this purpose are scarce. This study aims to create a fracture micro-CT image dataset, design deep learning algorithm segmentation, and develop an early model non-union. Methods Using animal models, images from 12 rats at various healing stages (days 1, 7, 14, 21, 28, 35) were analyzed. Fracture lesion frames annotated high-resolution dataset. We proposed the...
Abstract Background Chronic obstructive pulmonary disease (COPD) is a chronic respiratory that seriously threatens people’s health, with high morbidity and mortality worldwide. At present, the clinical diagnosis methods of COPD are time-consuming, invasive, radioactive. Therefore, it urgent to develop non-invasive rapid severity technique suitable for daily screening in practice. Results This study established an effective model preliminary using lung sounds few channels. Firstly,...
Background: Bone microstructure is important for evaluating bone strength and requires the support of high-resolution (HR) imaging equipment. Computed tomography (CT) widely used medical imaging, but spatial resolution not sufficient microstructure. Micro-CT scan data gold standard human or animal experiment. However, has more ionizing radiation longer scanning time while providing high-quality imaging. It makes sense to reconstruct HR images with less radiation. Image super-resolution (SR)...
Perioperative hyperoxia therapy is of great significance to save the lives patients, but little known about possible mechanisms that induce hyperoxia-induced acute lung injury (HALI) and measures for clinical prevention treatment. In this experiment, models were established with a feeding chamber automatic regulation oxygen concentration. The results showed increase in inhaled concentration prolongation exposure time, severity also increases significantly, reaching diagnostic indication HALI...
Hyperspectral imaging (HSI) is a popular method of substance identification and mapping in many fields. Light-emitting diodes (LEDs) can be introduced as an active light source, which have been widely used with the distinct advantages small size, low energy consumption, long lifetime, fast switching. In this paper, we propose HSI system that based on multi-wavelength LED-array source. This LED-based has simple stable configuration, without complex dispersive spectrometer mechanical scanning...
Myocardial bridges are congenital anatomical abnormalities in which myocardium covers a segment of coronary arteries, leading to stenocardia, myocardial ischemia, and sudden cardiac death severe cases. However, automatic diagnosis bridge presents significant challenges.A novel framework detection with x-ray angiography sequence is proposed, can realize vessel stenosis bridge. Firstly, we employ neural network model for segmentation, consists both CNNs transformer structures effectively...
Abstract Background There is a high incidence of injury to the lateral ligament ankle in daily living and sports activities. The anterior talofibular (ATFL) most frequent types injuries. It great clinical significance achieve intelligent localization evaluation ATFL due its vulnerability. Methods According specific characteristics bones different slices, key slice was extracted by image segmentation characteristic analysis. Then, talus fibula were segmented distance regularized level set...
Sleep apnea and hypopnea syndrome (SAHS) seriously affects sleep quality. In recent years, much research has focused on the detection of SAHS using various physiological signals algorithms. The purpose this study is to find an efficient model for apnea-hypopnea events based nasal flow SpO2 signals. A 60-s detector a 10-s were cascaded precise (AH) events. Random forests adopted classification data segments morphological features extracted from arterial blood oxygen saturation (SpO2). Then...
A stable animal model was needed to study bone non-union caused by insufficient blood supply, the main object of this paper is develop a medial malleolar fracture with controllable arterial vascular injuries in rats for revealing biochemical mechanism supply.A total 18 were randomly divided into three equal groups: Sham group, Fracture and + Vascular group. The animals subjected unilateral injury using customized molding equipment. site scanned micro-CT, evaluated laser Doppler flowmetry...