A5053746295- Neuroscience and Neural Engineering
- Advanced Memory and Neural Computing
- Photoreceptor and optogenetics research
- Image Processing Techniques and Applications
- AI in cancer detection
- Advanced Vision and Imaging
- Photoacoustic and Ultrasonic Imaging
- Optical Coherence Tomography Applications
- Advanced Neural Network Applications
- Genomic variations and chromosomal abnormalities
- Advanced Image and Video Retrieval Techniques
- Domain Adaptation and Few-Shot Learning
- Optical measurement and interference techniques
- EEG and Brain-Computer Interfaces
- Mechanical Behavior of Composites
- Advanced Fluorescence Microscopy Techniques
- Radiomics and Machine Learning in Medical Imaging
- Chromosomal and Genetic Variations
- Generative Adversarial Networks and Image Synthesis
- Brain Tumor Detection and Classification
- Cervical Cancer and HPV Research
- Robot Manipulation and Learning
- Digital Imaging for Blood Diseases
- Cell Image Analysis Techniques
- Face and Expression Recognition
Jilin Agricultural University
2025
Tiangong University
2022-2024
Shanghai Jiao Tong University
2015-2024
Nanjing University of Science and Technology
2023-2024
Tsinghua University
2024
Ministry of Education of the People's Republic of China
2015-2023
Peking University
2023
First Affiliated Hospital of Xi'an Jiaotong University
2022
Chongqing University of Education
2015
Chongqing University
2014
Detecting the marking characters of industrial metal parts remains challenging due to low visual contrast, uneven illumination, corroded character structures, and cluttered background part images. Affected by these factors, bounding boxes generated most existing methods locate low-contrast text areas inaccurately. In this paper, we propose a refined feature-attentive network (RFN) solve inaccurate localization problem. Specifically, design parallel feature integration mechanism construct an...
Visual prostheses based on a stimulating microelectrode array to restore vision offer promising approach for the blind and has become rapidly growing scientific field in neurorehabilitation engineering. A number of research groups from major developed countries lead activities this field. The goal C-Sight Project is develop an implantable microelectronic medical device that will useful patients. Retinitis pigmentosa (RP) age-related macular degeneration are two leading causes blindness,...
Photodynamic therapy (PDT) is an appealing treatment modality by producing reactive oxygen species (ROS) with photosensitizers (PSs) to induce cell apoptosis, but still suffering poor efficacy in treating hypoxic solid tumor. Herein, we have developed a nanocarrier (naming HAFeR) encapsulating PSs and RSL3 metal organic framework (MOF) for synergistic ferroptosis PDT. HAFeR nanocarriers selectively recognized CD44 overexpressed on tumor surface, were subsequently internalized via receptor...
Abstract Flow‐type electrolytic cell is a viable system for many electrochemical processes, in which gas‐diffusion electrode (GDE) plays vital role providing optimal reacting interfaces improved performances. Different from traditional GDEs with fixed porosity, here we propose new type of GDE that features flexible diffusion channels. Particularly, the has been assembled by pairing PTFE substrate Ag‐TCNQ/graphene hydrogels can be further manipulated through capillary compression. With...
This study designs and accomplishes a high precision robust laser-based autofocusing system, in which biased image plane is applied. In accordance to the designed optics, cluster-based circle fitting algorithm proposed calculate radius of detecting spot from reflected laser beam as an essential factor obtain defocus value. The experiment conduct on device achieved novel performance robustness. Furthermore, low demand assembly accuracy makes method low-cost realizable solution for technique.
This paper proposes a region sampling based autofocus method for rapid and robust in microscope. Image content size are considered criteria. An intelligent search algorithm which employs quartering hill climbing golden section is developed, rule-based evaluation of sampled focusing regions applied. Experimental results demonstrate that the proposed can significantly improve performance image-based autofocus.
In this paper, a deep learning based method is proposed to perform the basal membrane segmentation, which crucial prerequisite step in diagnosis of Microinvasive Carcinoma Cervix (MIC). We regard as an object contour segmentation problem and modify recently model with adversarial training strategy. Traditional networks contain generator discriminator. replace fully convolutional while keeping discriminator part training. evaluate our on challenging dataset collected by experienced...
Abstract Due to the high fiber volume fraction of carbon spread tow plain weave fabrics, it is difficult for short fibers be brought into thickness direction form needled bundles during needling process. The interlaminar performance preform weak, and in‐plane damage also severe. Responding this issue, article proposed a new method preparing based on yarn needling, which was expected manufacture high‐performance composite. We conducted experimental research preparation structural...
Visual prostheses offer a possibility of restoring useful reading ability to the blind. The psychophysics simulating with prosthesis using pixelized text has attracted attention recently. This study was an examination accuracy and efficiency Chinese paragraphs after different parameters were altered.Forty native speakers normal or corrected visual acuity (20/20) participated in four experiments. Reading measured changing character resolution, size, pixel dropout percentage, number gray...
Due to the limitations on depth of field high-resolution fluorescence microscope, it is difficult obtain an image with all objects in focus. The existing fusion methods suffer from blocking effects or out-of-focus fluorescence. proposed multi-focus method based local maximum luminosity, intensity variance and information filling can reconstruct all-in-focus image. Moreover, tissue's surface be estimated 3D model.
Prenatal screening of chromosomal abnormalities is an important means ensuring the healthy survival rate newborns. The complex information and tedious workload chromosome karyotype image analysis a major difficulty in medical diagnosis. In this paper, preprocessing model with object segmentation feature enhancement proposed. Combined framework deep learning network, automatic classification for recognition chromosomes constructed. studies extraction images at pixel level images. aims...