A5100325209- Retinal Imaging and Analysis
- Glaucoma and retinal disorders
- Retinal Diseases and Treatments
- Optical Coherence Tomography Applications
- Digital Imaging for Blood Diseases
- Medical Image Segmentation Techniques
- Retinal and Optic Conditions
- Advanced Neural Network Applications
- AI in cancer detection
- Corneal surgery and disorders
- Image Processing Techniques and Applications
- Anomaly Detection Techniques and Applications
- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Advanced Vision and Imaging
- Advanced Image and Video Retrieval Techniques
- Image Retrieval and Classification Techniques
- Surgical Simulation and Training
- Robotics and Sensor-Based Localization
- Domain Adaptation and Few-Shot Learning
- Gastric Cancer Management and Outcomes
- Ocular Surface and Contact Lens
- Lung Cancer Treatments and Mutations
- COVID-19 diagnosis using AI
- Advanced Image Processing Techniques
Southern University of Science and Technology
2019-2025
Harbin Medical University
2024-2025
Second Affiliated Hospital of Harbin Medical University
2024-2025
University of Nottingham Ningbo China
2021-2025
Harbin Institute of Technology
2022-2025
Wenzhou Medical University
2021-2025
Chinese PLA General Hospital
2014-2025
Lanzhou University
2025
University of Shanghai for Science and Technology
2021-2025
Sichuan Agricultural University
2025
Glaucoma is a chronic eye disease that leads to irreversible vision loss. The cup disc ratio (CDR) plays an important role in the screening and diagnosis of glaucoma. Thus, accurate automatic segmentation optic (OD) (OC) from fundus images fundamental task. Most existing methods segment them separately, rely on hand-crafted visual feature images. In this paper, we propose deep learning architecture, named M-Net, which solves OD OC jointly one-stage multi-label system. proposed M-Net mainly...
Medical image segmentation is an important step in medical analysis. With the rapid development of a convolutional neural network processing, deep learning has been used for segmentation, such as optic disc blood vessel detection, lung cell and so on. Previously, U-net based approaches have proposed. However, consecutive pooling strided operations led to loss some spatial information. In this paper, we propose context encoder (CE-Net) capture more high-level information preserve 2D...
Glaucoma is a chronic eye disease that leads to vision loss. As it cannot be cured, detecting the in time important. Current tests using intraocular pressure (IOP) are not sensitive enough for population based glaucoma screening. Optic nerve head assessment retinal fundus images both more promising and superior. This paper proposes optic disc cup segmentation superpixel classification In segmentation, histograms, center surround statistics used classify each as or non-disc. A self-assessment...
In real-world crowd counting applications, the densities vary greatly in spatial and temporal domains. A detection based method will estimate crowds accurately low density scenes, while its reliability congested areas is downgraded. regression approach, on other hand, captures general information crowded regions. Without knowing location of each person, it tends to overestimate count areas. Thus, exclusively using either one them not sufficient handle all kinds scenes with varying densities....
Glaucoma is a chronic and irreversible eye disease, which leads to deterioration in vision quality of life. In this paper, we develop deep learning (DL) architecture with convolutional neural network for automated glaucoma diagnosis. Deep systems, such as networks (CNNs), can infer hierarchical representation images discriminate between non-glaucoma patterns diagnostic decisions. The proposed DL contains six learned layers: four layers two fully-connected layers. Dropout data augmentation...
Retinal fundus image is an important modality to document the health of retina and widely used diagnose ocular diseases such as glaucoma, diabetic retinopathy age-related macular degeneration. However, enormous amount retinal data obtained nowadays mostly stored locally; valuable embedded clinical knowledge not efficiently exploited. In this paper we present online depository, ORIGA(-light), which aims share groundtruth images with public; provide open access for researchers benchmark their...
Vessel segmentation is a key step for various medical applications. This paper introduces the deep learning architecture to improve performance of retinal vessel segmentation. Deep has been demonstrated having powerful ability in automatically rich hierarchical representations. In this paper, we formulate boundary detection problem, and utilize fully convolutional neural networks (CNNs) generate probability map. Our map distinguishes vessels background inadequate contrast region, robustness...
Optical Coherence Tomography Angiography (OCTA) is a non-invasive imaging technique that has been increasingly used to image the retinal vasculature at capillary level resolution. However, automated segmentation of vessels in OCTA under-studied due various challenges such as low visibility and high vessel complexity, despite its significance understanding many vision-related diseases. In addition, there no publicly available dataset with manually graded for training validation algorithms. To...
Glaucoma is a chronic eye disease that leads to irreversible vision loss. Most of the existing automatic screening methods firstly segment main structure, and subsequently calculate clinical measurement for detection glaucoma. However, these measurement-based rely heavily on segmentation accuracy, ignore various visual features. In this paper, we introduce deep learning technique gain additional image-relevant information, screen glaucoma from fundus image directly. Specifically, novel...
Abstract Understanding genetic architecture of plasma lipidome could provide better insights into lipid metabolism and its link to cardiovascular diseases (CVDs). Here, we perform genome-wide association analyses 141 species (n = 2,181 individuals), followed by phenome-wide scans with 25 CVD related phenotypes 511,700 individuals). We identify 35 lipid-species-associated loci (P <5 ×10 −8 ), 10 which associate risk including five new loci- COL5A1 , GLTPD2 SPTLC3 MBOAT7 GALNT16 (false...
The development of medical imaging techniques has greatly supported clinical decision making. However, poor quality, such as non-uniform illumination or imbalanced intensity, brings challenges for automated screening, analysis and diagnosis diseases. Previously, bi-directional GANs (e.g., CycleGAN), have been proposed to improve the quality input images without requirement paired images. these methods focus on global appearance, imposing constraints structure illumination, which are...
In this work, instead of directly predicting the pixel-level segmentation masks, problem referring image seg-mentation is formulated as sequential polygon generation, and predicted polygons can be later converted into masks. This enabled by a new sequence-to-sequence framework, Polygon Transformer (PolyFormer), which takes sequence patches text query to-kens input, outputs vertices autoregressively. For more accurate geometric localization, we propose regression-based decoder, predicts...
Glaucoma is a leading cause of permanent blindness. However, disease progression can be limited if detected early. The optic cup-to-disc ratio (CDR) one the main clinical indicators glaucoma, and currently determined manually, limiting its potential in mass screening. In this paper, we propose an automatic CDR determination method using variational level-set approach to segment disc cup from retinal fundus images. core component ARGALI, system for automated glaucoma risk assessment....
Integrin α11β1 is a stromal cell-specific receptor for fibrillar collagens and overexpressed in carcinoma-associated fibroblasts (CAFs). We have investigated its direct role cancer progression by generating severe combined immune deficient (SCID) mice integrin α11 (α11) expression. The growth of A549 lung adenocarcinoma cells two patient-derived non-small cell carcinoma (NSCLC) xenografts these knockout (α11−/−) was significantly impeded, as compared with wild-type (α11+/+) SCID mice....
The detection of retinal vessel is great importance in the diagnosis and treatment many ocular diseases. Many methods have been proposed for detection. However, most algorithms neglect connectivity vessels, which plays an important role diagnosis. In this paper, we propose a novel method includes dense dilated network to get initial vessels probability regularized walk algorithm address fracture issue integrates newly feature extraction blocks into encoder-decoder structure extract...