A5100336500- Optical measurement and interference techniques
- Advanced Measurement and Metrology Techniques
- Liver Disease Diagnosis and Treatment
- Medical Image Segmentation Techniques
- Optical Systems and Laser Technology
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Adaptive optics and wavefront sensing
- Hepatocellular Carcinoma Treatment and Prognosis
- Natural Language Processing Techniques
- Artificial Intelligence in Healthcare
- Topic Modeling
- Brain Tumor Detection and Classification
- Surface Roughness and Optical Measurements
- Image Processing Techniques and Applications
- Advanced optical system design
- Image and Object Detection Techniques
- Privacy-Preserving Technologies in Data
- Advanced Computational Techniques and Applications
- Image Retrieval and Classification Techniques
- Dental Radiography and Imaging
- Multimodal Machine Learning Applications
- Hepatitis B Virus Studies
- Face and Expression Recognition
- Infrared Thermography in Medicine
Guangxi University
2016-2025
Hunan Normal University
2025
Capital Medical University
2024
Lanzhou Jiaotong University
2015-2024
Xinjiang Academy of Agricultural Sciences
2024
Xidian University
2024
Anhui University
2024
Beijing Children’s Hospital
2024
Chinese Academy of Sciences
2008-2023
Changchun Institute of Optics, Fine Mechanics and Physics
2013-2023
The purpose of our study was to preliminarily evaluate the usefulness a computer algorithm analysis using finite difference method and an artificial neural network diagnose hepatic fibrosis with MR images.Liver parenchymal textures on images 52 patients who underwent partial hepatectomy were processed by reviewed two radiologists. texture features program containing three-layer learning back propagation, composed seven-unit input layer, six-unit hidden one-unit output layer. radiologists...
Fringe projector profilometry (FPP) is an important three-dimensional (3D) measurement technique, especially when high precision and speed are required. Thus, theoretical interrogation critical to provide deep understanding possible improvement of FPP. By dividing FPP process into four steps (system calibration, phase measurement, pixel correspondence, 3D reconstruction), we give analysis on the entire except for extensively studied calibration step. Our study indeed reveals a series system...
Ameloblastoma (AM), periapical cyst (PC), and chronic suppurative osteomyelitis (CSO) are prevalent maxillofacial diseases with similar imaging characteristics but different treatments, thus making preoperative differential diagnosis crucial. Existing deep learning methods for often require manual delineation in tagging the regions of interest (ROIs), which triggers some challenges practical application. We propose a new model Wavelet Extraction Fusion Module Vision Transformer...
Malocclusions are a type of cranio-maxillofacial growth and developmental deformity that occur with high incidence in children. Therefore, simple rapid diagnosis malocclusions would be great benefit to our future generation. However, the application deep learning algorithms automatic detection children has not been reported. aim this study was develop learning-based method for classification sagittal skeletal pattern validate its performance. This first step establishing decision support...
The early symptom of lung tumor is always appeared as nodule on CT scans, among which 30% to 40% are malignant according statistics studies. Therefore, detection and classification nodules crucial the treatment cancer. With increasing prevalence cancer, large amount images waiting for diagnosis huge burdens doctors who may missed or false detect abnormalities due fatigue. Methods: In this study, we propose a novel method based YOLOv3 deep learning algorithm with only one preprocessing step...
Traditional methods for distortion measurement of large-aperture optical systems are time-consuming and ineffective because they require each field view to be individually measured using a high-precision rotating platform. In this study, new method that uses phase diffractive beam splitter (DBS) is proposed measure the systems, which has great potential application system. The very high degree accuracy extremely economical. A calibration angular distribution DBS. uncertainty analysis factors...
With the popularity of smart devices and widespread use Wi-Fi-based indoor localization, edge computing is becoming mainstream paradigm processing massive sensing data to acquire localization service. However, these which were conveyed train model unintentionally contain some sensitive information users/devices, released without any protection may cause serious privacy leakage. To solve this issue, we propose a lightweight differential privacy-preserving mechanism for environment. We extend...
This study introduces Multi-Threshold Recurrence Rate Plots (MTRRP), a novel methodology for analyzing dynamic patterns in complex systems, such as those influenced by neurodegenerative diseases brain activity. MTRRP characterizes how recurrence rates evolve with increasing thresholds. A key innovation of our approach, Complexity, captures structural complexity integrating local randomness and global features through the product Gradient Hurst, both derived from MTRRP. We applied this...
Artificial intelligence has been applied to medical diagnosis and decision-making but it not used for classification of Class III malocclusions in children. Objective: This study aims propose an innovative machine learning (ML)-based diagnostic model automatically classifies dental, skeletal functional malocclusions. Methods: The collected data related 46 cephalometric feature measurements from 4–14-year-old children (n = 666). set was divided into a training test 7:3 ratio. Initially, we...