A5101666192- Virtual Reality Applications and Impacts
- Visual perception and processing mechanisms
- Advanced Optical Imaging Technologies
- Radiomics and Machine Learning in Medical Imaging
- Ophthalmology and Visual Impairment Studies
- Stroke Rehabilitation and Recovery
- Retinal Imaging and Analysis
- AI in cancer detection
- Medical Imaging and Analysis
- Blood Pressure and Hypertension Studies
- SARS-CoV-2 detection and testing
- Advanced Bandit Algorithms Research
- Tunneling and Rock Mechanics
- Advanced Image Fusion Techniques
- Rock Mechanics and Modeling
- COVID-19 epidemiological studies
- Colorectal and Anal Carcinomas
- Pharmaceutical studies and practices
- Interactive and Immersive Displays
- Domain Adaptation and Few-Shot Learning
- Random lasers and scattering media
- Reinforcement Learning in Robotics
- Attention Deficit Hyperactivity Disorder
- Underwater Acoustics Research
- Advanced Neural Network Applications
University of Science and Technology of China
2018-2024
Chinese Academy of Sciences
2024
University of Illinois Urbana-Champaign
2021
Sun Yat-sen University
2018-2021
3M (United States)
2021
University of Toronto
2021
Purdue Pharma (Canada)
2021
State Key Laboratory of Optoelectronic Materials and Technology
2019
Huazhong University of Science and Technology
2019
Center of Hubei Cooperative Innovation for Emissions Trading System
2019
It is highly challenging for the available glasses-free 3D display to simultaneously possess advantages of viewing freedom, homogeneous illuminance, high resolution and low crosstalk. This work proposes demonstrates a directional backlight autostereoscopic having these with substantially extended volume densely packed viewpoints. Low crosstalk illuminance are obtained using dynamically configured backlight, realized by novel system design, in conjunction viewer’s eye tracking subsequent...
Data generated in clinical practice often exhibits biases, such as long-tail imbalance and algorithmic unfairness. This study aims to mitigate these challenges through data synthesis. Previous efforts medical imaging synthesis have struggled with separating lesion information from background context, leading difficulties generating high-quality backgrounds limited control over the synthetic output. Inspired by diffusion-based image inpainting, we propose LeFusion, lesion-focused diffusion...
Virtual reality (VR) technology is increasingly used in stroke rehabilitation. This study aimed to investigate the effectiveness of using glasses-free VR training improve motor function upper limb patients with stroke. Twelve were recruited participate intervention 3 weeks. At baseline and post intervention, two times evaluation including Fugl-Meyer upper-extremity scale (FMS-UE), transcranial magnetic stimulation (TMS) measurement motion performed. No significant difference was observed...
In the Fall of 2020, many universities saw extensive transmission SARS-CoV-2 among their populations, threatening health students, faculty and staff, viability in-person instruction, surrounding communities. 1, 2 Here we report that a multimodal “SHIELD: Target, Test, Tell” program mitigated spread at large public university, prevented community transmission, allowed continuation classes amidst pandemic. The combines epidemiological modelling surveillance (Target); fast frequent testing...
Abstract Imaging delivering to correct retina assisted with tracking technique is a common practice for autostereoscopic displays stereo two‐view data format. Due various latencies produced in camera buffering, computer processing, transmission, and illumination refreshing, delayed image delivery will give rise substantial degradation of the 3D display experience. This particularly obvious directional backlight where significant flickering resulted as result inherent latency. work...
Rectal cancer segmentation of CT image plays a crucial role in timely clinical diagnosis, radiotherapy treatment, and follow-up. Although current methods have shown promise delineating cancerous tissues, they still encounter challenges achieving high precision. These obstacles arise from the intricate anatomical structures rectum difficulties performing differential diagnosis rectal cancer. Additionally, major obstacle is lack large-scale, finely annotated dataset for segmentation. To...
Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental that begins in childhood and often persists into adulthood. ADHD increases the risk of various negative impacts, pharmacists are well positioned to address these issues community.This survey study aims first identify pharmacists' knowledge gaps experience with management second assess their preferences for continuing education sleep-related ADHD.A was sent Part A Ontario active licenses who opted receive research-related...
Accurate segmentation of metastatic lymph nodes in rectal cancer is crucial for the staging and treatment cancer. However, existing approaches face challenges due to absence pixel-level annotated datasets tailored around rectum. Additionally, are characterized by their relatively small size, irregular shapes, lower contrast compared background, further complicating task. To address these challenges, we present first large-scale perirectal node CT image dataset called Meply, which encompasses...
Background: Rectal cancer segmentation in CT is crucial for timely diagnosis. Despite promising methods, challenges remain due to the rectum's complex anatomy and lack of a comprehensive annotated dataset.Methods: A total 33,024 slice pairs from 398 rectal patients new source single center were enrolled into our dataset, named CARE Dataset, with pixel-level annotations both normal cancerous rectum tissue. We split it 317 cases training 81 testing. Additionally, we introduce novel model,...
This study aimed to develop an interactive vision screening tool based on desktop autostereoscopy and evaluate its feasibility for testing visual acuity, colour vision, stereo binocular balance clinically.An test was developed making it remarkably convenient individuals undergo multiple function assessments in a single test. With this rapid process, individual's can be assessed within several minutes. A total of 155 healthy subjects were enrolled compare the clinical repeatability, accuracy,...
We study the problem of best arm identification in multi-armed bandits, where underlying setting can be either stochastic or adversarial and is not revealed to forecaster a priori. propose an algorithm, called S3-BA, whose key idea simultaneously explore arms learn model, switch when declared. analyze performance proposed algorithm for both bandits. For bandits we prove upper bound on error rate S3-BA that same order as UCB-E SH. show guaranteed long budget above threshold. More importantly,...
Different from conventional head‐mounted virtual reality, we achieve a high quality glasses‐free reality (VR) platform by combining full HD directional backlight 3D display with gesture controller. The VR enables resolution, low crosstalk and wide viewing angle, which is able to provide precise depth information. Attributed the excellent effect without any assisting goggles, our can be used for rehabilitation of stroke patients. Compared traditional 2D training, it offers third dimension...
with the development of virtual reality technology, a new system related to vision would have been proposed, which not only enable myope people screen their independently but also makes it possible improve people's vision. In addition, will reduce labor and medical consumables in visual acuity screening.
Flicker is one of the most prominent issues in directional backlight autostereoscopic displays. This work studies flicker characterization over entire screen with a high‐speed camera. The method shows that it works well to adapt practical visual experience and gives global quantitative description flicker. An artificial intelligent scheme motion prediction established reduce flicker, which proved be effective.
with the development of virtual reality technology, a new system related to vision would have been proposed, which not only enable myope people screen their independently but also makes it possible improve people’s vision. In addition, will reduce labor and medical consumables in visual acuity screening.