A5100646840- Advanced Optical Imaging Technologies
- COVID-19 diagnosis using AI
- Radiomics and Machine Learning in Medical Imaging
- Virtual Reality Applications and Impacts
- Lung Cancer Diagnosis and Treatment
- Advanced MRI Techniques and Applications
- Interactive and Immersive Displays
- Image and Video Stabilization
- Photorefractive and Nonlinear Optics
- Hepatocellular Carcinoma Treatment and Prognosis
- Parkinson's Disease Mechanisms and Treatments
- Liquid Crystal Research Advancements
- Cardiac Valve Diseases and Treatments
- Neurological disorders and treatments
- Diet and metabolism studies
- Cardiac Imaging and Diagnostics
- Medical Imaging Techniques and Applications
- Privacy-Preserving Technologies in Data
- Medical Image Segmentation Techniques
- Phonocardiography and Auscultation Techniques
- Cancer Treatment and Pharmacology
- Image Enhancement Techniques
- Advanced Neuroimaging Techniques and Applications
- Cardiac Arrest and Resuscitation
- Advanced Neural Network Applications
Massachusetts General Hospital
2020-2025
Harvard University
2020-2025
First Hospital of Jilin University
2021-2024
Jilin University
2018-2024
Peking University Cancer Hospital
2023-2024
Guangzhou Blood Center
2024
First Affiliated Hospital of Kunming Medical University
2022-2024
Kunming Medical University
2022-2024
Peking University
2019-2024
Zhejiang University
2024
Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining anonymity, thus removing many barriers to sharing. Here we 20 institutes across the globe train FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts future oxygen requirements of symptomatic patients COVID-19 using inputs vital signs, laboratory and X-rays. achieved an average area under curve (AUC) >0.92 predicting...
Integral imaging is a promising three-dimensional (3D) technique that captures and reconstructs light field information. Microlens arrays are usually used for the reconstruction process to display 3D scenes viewer. However, inherent chromatic aberration of microlens array reduces viewing quality, thus, broadband achromatic remains challenge integral imaging. Here, we realize silicon nitride metalens in visible region can be reconstruct optical white light. The contains 60 ×...
Light field 3D display technology is considered a revolutionary to address the critical visual fatigue issues in existing displays. Tabletop light provides brand-new form that satisfies multi-user shared viewing and collaborative works, it poised become potential alternative traditional wall portable forms. However, large radial angle correct perspective parallax are still out of reach for most current tabletop displays due limited amount spatial information. To issues, novel integral...
Despite achieving impressive results in general-purpose semantic segmentation with strong generalization on natural images, the Segment Anything Model (SAM) has shown less precision and stability medical image segmentation. In particular, SAM architecture is designed for 2D images therefore not support to handle three-dimensional information, which particularly important imaging modalities that are often volumetric or video data. this paper, we introduce MediViSTA, a parameter-efficient...
To explore the relationship between college students' alexithymia and mobile phone addiction as well mediating effects of mental health moderating role being a single child or not. A total 1034 students from Changchun were assessed with Toronto Alexithymia Scale (TAS-20), General Health Questionnaire (GHQ) Mobile Phone Addiction Index (MPAI). was positively correlated addiction. had not only direct impact on but also an indirect via health. For who children, higher levels led to increase in...
Dynamic computed tomography perfusion (CTP) imaging is a promising approach for acute ischemic stroke diagnosis and evaluation. Hemodynamic parametric maps of cerebral parenchyma are calculated from repeated CT scans the first pass iodinated contrast through brain. It necessary to reduce dose CTP routine applications due high radiation exposure scans, where image denoising achieve reliable diagnosis. In this article, we proposed self-supervised deep learning method denoising, which did not...
As of August 30th, there were in total 25.1 million confirmed cases and 845 thousand deaths caused by coronavirus disease 2019 (COVID-19) worldwide. With overwhelming demands on medical resources, patient stratification based their risks is essential. In this multi-center study, we built prognosis models to predict severity outcomes, combining patients' electronic health records (EHR), which included vital signs laboratory data, with deep learning- CT-based prediction.
Abstract ‘Federated Learning’ (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the thus removing many barriers sharing. During SARS-COV-2 pandemic, 20 institutes collaborated on healthcare FL study predict future oxygen requirements infected patients using inputs vital signs, laboratory data, and chest x-rays, constituting “EXAM” (EMR CXR AI Model) model. EXAM achieved an average Area Under Curve (AUC) over 0.92,...
Imaging plays an important role in assessing the severity of COVID-19 pneumonia. Recent research indicates that disease progress propagates from bottom lungs to top. However, chest radiography (CXR) cannot directly provide a quantitative metric radiographic opacities, and existing AI-assisted CXR analysis methods do not quantify regional severity. In this paper, assist analysis, we developed fully automated framework using deep learning-based four-region segmentation detection models...
Evidence concerning long-term outcome of robotic liver resection (RLR) and laparoscopic (LLR) for hepatocellular carcinoma (HCC) patients is scarce.
<title>Abstract</title> Precise and explainable alignment between data from different modalities is crucial for advancing artificial general intelligence in medicine. In this work, we present CAMMAL (Cyclic Adaptive Medical Modality ALignment), a framework that can achieve fine-grained vision-language through two key innovations, including an Patch-Word Matching (AdaMatch) mechanism dynamically correlates regions medical images with specific words radiology reports, bidirectional generative...
Early and accurate diagnosis of Coronavirus disease (COVID-19) is essential for patient isolation contact tracing so that the spread infection can be limited. Computed tomography (CT) provide important information in COVID-19, especially patients with moderate to severe as well those worsening cardiopulmonary status. As an automatic tool, deep learning methods utilized perform semantic segmentation affected lung regions, which establish severity prognosis prediction. Both extent type...
Abstract Tabletop three‐dimensional (3D) display is an attractive technology that allows multiple individuals around the table to view reconstructed 3D objects simultaneously, which can be applied a variety of application scenarios such as desktop conference and board games. In this review paper, tabletop true has been characterized classified into four categories based on technologies light field display, integral imaging, volumetric holographic displays. Moreover, comparisons these are...
In this paper, we propose a scheme based on sparse camera array and convolution neural network super-resolution for super-multiview integral imaging. particular, the proposed is adequate to not only virtual-world three-dimensional scene with high performance efficiency, but also real-world 3D higher availability than traditional methods. scheme, first adopt strategy capture viewpoint images use these synthesize low-resolution elemental image array, then used restore high-resolution from...
Constitutively active KRAS mutations have been found to be involved in various processes of cancer development, and render tumor cells resistant EGFR-targeted therapies. Mutation detection methods with higher sensitivity will increase the possibility choosing correct individual therapy. Here, we established a highly sensitive efficient microfluidic capillary electrophoresis-based restriction fragment length polymorphism (µCE-based RFLP) platform for low-abundance genotyping combination µCE...
We propose an optical method to eliminate pseudoscopic issue in the integral imaging three-dimensional (3D) display by using a transmissive mirror device (TMD) and light filter. Object rays passing through TMD can form undistorted depth inverted real image. Therefore, existing traditional imaging. However, two ghost images appeared TMD. After studying causes of images, filter is designed fabricated images. Integral developed, it presents high quality 3D image without issue.
Two-dimensional (2D)/three-dimensional (3D) convertible or mixed display is one of the most important factors for fast penetration 3D into market. In this paper, we propose a 2D/3D frontal projection system that mainly contains liquid crystal micro-lens array (LCMLA) and quarter-wave retarding film with pinholes (QWRF-P). The LCMLA exhibits focusing effect no optical depending on polarization direction incident lights. forward lights pass through without any bending. After passing QWRF-P...