A5062660870- Visual perception and processing mechanisms
- Spectroscopy and Chemometric Analyses
- Smart Agriculture and AI
- Glaucoma and retinal disorders
- Retinal Imaging and Analysis
- Corneal surgery and disorders
- Advanced Vision and Imaging
- Empathy and Medical Education
- Non-Invasive Vital Sign Monitoring
- Bone and Joint Diseases
- Hip disorders and treatments
- Statistical and numerical algorithms
- Remote Sensing and Land Use
- Orthopaedic implants and arthroplasty
- Cardiac Valve Diseases and Treatments
- Water Quality Monitoring and Analysis
- Psychology of Moral and Emotional Judgment
- Diabetic Foot Ulcer Assessment and Management
- Medical Imaging and Analysis
- Ophthalmology and Visual Impairment Studies
University of Toronto
2020-2024
Huazhong Agricultural University
2022
Fujian Agriculture and Forestry University
2020
Central China Normal University
2015
Health and Human Development (2HD) Research Network
2015
Perimetry and optical coherence tomography (OCT) are both used to monitor glaucoma progression. However, combining these modalities can be a challenge due differences in data types. To overcome this, we have developed an autoencoder fusion (AEDF) model learn compact encoding (AE-fused data) from perimetry OCT. The AEDF model, optimized specifically for visual field (VF) progression detection, incorporates loss ensure the interpretation of AE-fused is similar VF while capturing key features...
As the first diagnostic imaging modality of avascular necrosis femoral head (AVNFH), accurately staging AVNFH from a plain radiograph is critical yet challenging for orthopedists. Thus, we propose deep learning-based diagnosis system (AVN-net). The proposed AVN-net reads radiographs pelvis, conducts diagnosis, and visualizes results automatically. Deep convolutional neural networks are trained to provide an end-to-end solution, covering tasks detection, exam-view identification, side...
For accurate recognition of orange fruit targets, a detection algorithm based on YOLOv4 was applied in this research. The results showed that AP (average precision) had reached 98.17%, 2.14% and 2.67% respectively higher than SSD Faster RCNN while rate traditional image processing algorithms merely 54.94%. Additionally, the extent occlusion proved to have obvious influences accuracy detection. slight conditions appeared be serious conditions. Generally, its feasibility superiority complex...
Perimetry, or visual field test, estimates differential light sensitivity thresholds across many locations in the (e.g., 54 24–2 grid). Recent developments have shown that an entire may be relatively accurately reconstructed from measurements of a subset these using linear regression model. Here, we show incorporating dimensionality reduction layer can improve robustness this reconstruction. Specifically, propose to use principal component analysis transform training dataset lower...
Bayesian adaptive methods for sensory threshold determination were conceived originally to track a single threshold. When applied the testing of vision, they do not exploit spatial patterns that underlie thresholds at different locations in visual field. Exploiting these has been recognized as key further improving field test efficiency. We present new approach (TORONTO) outperforms other existing terms speed and accuracy. TORONTO generalizes QUEST/ZEST algorithm estimate simultaneously...
摘要:
As the first-line diagnostic imaging modality, radiography plays an essential role in early detection of developmental dysplasia hip (DDH). Clinically, diagnosis DDH relies on manual measurements and subjective evaluation different anatomical features from pelvic radiographs. This process is inefficient error-prone requires years clinical experience. In this study, we propose a deep learning-based system that automatically detects 14 keypoints radiograph, measures three angles (center-edge,...