A5100759529- Image and Signal Denoising Methods
- Advanced Image Processing Techniques
- Advanced Image Fusion Techniques
- Image Processing Techniques and Applications
- Advanced Measurement and Detection Methods
- Medical Image Segmentation Techniques
- Remote Sensing and Land Use
- Advanced Steganography and Watermarking Techniques
- Smart Agriculture and AI
- Advanced Vision and Imaging
- Advanced Fiber Optic Sensors
- Image and Video Stabilization
- Video Surveillance and Tracking Methods
- Advanced Neural Network Applications
- Optical Systems and Laser Technology
- Photonic and Optical Devices
- Advanced Computational Techniques and Applications
- Traditional Chinese Medicine Studies
- Adaptive optics and wavefront sensing
- Advanced Chemical Physics Studies
- Optical measurement and interference techniques
- Image Retrieval and Classification Techniques
- Embedded Systems and FPGA Design
- Digital Media Forensic Detection
- Digital Imaging for Blood Diseases
Nanjing University
2025
Sun Yat-sen University
2019-2025
The First Affiliated Hospital, Sun Yat-sen University
2019-2025
Fuzhou University
2025
Nanchang University
2025
Jilin Agricultural University
2012-2024
Hangzhou Institute of Applied Acoustics
2018-2024
Inner Mongolia University
2024
Xiamen University Malaysia
2023
Dalian Minzu University
2023
The invasion of agricultural diseases and insect pests is a huge difficulty for the growth crops. detection very challenging task. diversity in terms shapes, colors, sizes, as well changes lighting environment, have massive impact on accuracy results. We improved C2F module based DenseBlock proposed DCF to extract low-level features such edge texture diseases. Through sensitivity diseases, can better cope with complex tasks improve robustness detection. background environment different...
Purpose: To assess focal cerebral perfusion in patients with refractory depressive disorder (RDD), nonrefractory (NDD), and healthy control subjects by using arterial spin-labeling (ASL) magnetic resonance (MR) imaging. Materials Methods: This study was approved the local ethical committee, written informed consent obtained from all participants. Twenty-four RDD, 37 NDD, 42 were included. From February 2006 to July 2007, participants imaged a 3-T MR system. ASL echo-planar images subtracted...
Retinal image processing is very important in the field of clinical medicine.As first step retinal processing, enhancement essential.Because details a are complex and difficult to enhance, we present robust algorithm via dual-tree wavelet transform (DTCWT) morphology-based method this paper.To begin with, utilize pre-processing captured images.Then, DTCWT applied decompose gray obtain high-pass subbands low-pass subbands.Then, Contourlet-based subbands.For subbands, improve morphology...
<title>Abstract</title> Background To investigate factors associated with liver regeneration capacity in patients hepatocellular carcinoma (HCC) after resection. Methods A total of 123 HCC who underwent stiffness (LS) measurement by two-dimensional shear wave elastography (2D-SWE) before resection were retrospectively included. The future remnant (FLR) and postoperative volume (PLV) measured. standardized (sFLR), parenchymal hepatic rate (PHRR), index (RI) calculated. Patients classified...
In recent years, the research and application of ginseng, a famous valuable medicinal herb, has received extensive attention at home abroad. However, with gradual increase in demand for discrepancies are inevitable when using traditional manual method grading appearance quality ginseng. Addressing these challenges was primary focus this study. This study obtained batch ginseng samples enhanced dataset by data augmentation, based on which we refined YOLOv8 network three key dimensions:...
A fiber optic vector hydrophone is an interesting topic for many applications. Using a Bragg grating (FBG) as reflection unit, the combines advantages of miniaturization, high reliability, and low cost. In this paper, interferometric sensing, multiplexing design, cross-talk suppression based on FBG-based Fabry-Perot interferometry are discussed validated. The average cross talk channels reduced by 20 dB than that high-reflectivity using 1% reflectivity gratings. three-component...
Sirtuin 1 (SIRT1) is a class III histone deacetylase that exerts an anti-inflammatory effect in airway diseases. Activated macrophages play important role asthma. However, the roles of SIRT1 on allergic inflammation remain largely unexplored. In this study, we aimed to determine macrophages. The myeloid-specific deletion (Sirt1fl/fl-LysMcre) was assessed by using vivo models asthma following allergen exposure and vitro culture primary bone marrow–derived (BMDMs) exposed house dust mite...
This paper proposes a method for recognizing the origin of Saposhnikovia divaricata using IResNet model to achieve computer vision-based classification. Firstly, we created small sample dataset and applied data augmentation techniques enhance its diversity. After that, introduced hierarchical residual connection block in early stage original expand perceptual field neural network extraction scale features. Meanwhile, depth-separable convolution operation was adopted later replace...
This paper based on the analysis of basic meaning in data mining and structure decision tree uses algorithm — C4.5 to establish a soil quality grade prediction model combines composition Lishu be training sample. also expresses acquired knowledge by means quantitative rules. The experiment results manifest that expression algorithm's is easy understand, convenient for practical application, improves forecasting accuracy provides reliable theoretical basis precision fertilization.
Purpose: Particulate matter (PM) has been implicated as a risk factor for airway injury. However, the molecular mechanisms remain largely unclear. The goal of this study was to determine whether sirtuin1 (SIRT1), an anti-inflammatory and antiaging protein, protects against PM-induced inflammation. Methods: effect SIRT1 on inflammation assessed by using in vivo models induced PM vitro culture human bronchial epithelial (HBE) cells exposed PM, resveratrol (SIRT1 activator), or both. Results:...
For the analysis of medical images, one most basic methods is to diagnose diseases by examining blood smears through a microscope check morphology, number, and ratio red cells white cells. Therefore, accurate segmentation cell images essential for counting identification. The aim this paper perform smear image combining neural ordinary differential equations (NODEs) with U-Net networks improve accuracy segmentation. In order study effect ODE-solve on speed network, ODE-block module was added...
Monitoring the morphology of blood leukocytes, plays an important role in medical research, especially treatment diseases such as immunodeficiency. Traditional manual detection methods are susceptible to numerous interference factors. Therefore, cells often segmented using deep-learning algorithms. This study proposes a U-Net model based on combination attention mechanism and dilated convolutions. First, traditional convolution double convolutional module network is replaced by convolution,...
In the academic world, ginseng (Panax C. A. Meyer) has received much attention as most representative element of Chinese medicine. To address lack traditional algorithms in identification appearance quality and further improve manual on ginseng, we propose a grading method based deep learning, taking advantage benefits learning image identification. Firstly, substituted LeakyReLU for conventional activation function ReLU to enhance predictive power model. Secondly, added an ECA module...
An adaptive optics (AO) system provides real-time compensation for atmospheric turbulence. However, an AO image is usually of poor contrast because the nature imaging process, meaning that contains information coming from both out-of-focus and in-focus planes object, which also brings about a loss in quality. In this paper, we present robust multi-frame restoration algorithm via maximum likelihood estimation. Our proposed uses method with regularization as basic principle, constructs joint...