A5030671553- Retinal Diseases and Treatments
- Glaucoma and retinal disorders
- Retinal and Optic Conditions
- Retinal Imaging and Analysis
- Ocular Diseases and Behçet’s Syndrome
- Neuroinflammation and Neurodegeneration Mechanisms
- Retinal Development and Disorders
- Intraocular Surgery and Lenses
- Ocular Surface and Contact Lens
- Corneal surgery and disorders
- Ophthalmology and Visual Impairment Studies
- COVID-19 Clinical Research Studies
- Retinopathy of Prematurity Studies
- Ocular Infections and Treatments
- Cell death mechanisms and regulation
- Retinoids in leukemia and cellular processes
- Corneal Surgery and Treatments
- COVID-19 diagnosis using AI
- Genomics and Phylogenetic Studies
- Toxoplasma gondii Research Studies
- SARS-CoV-2 and COVID-19 Research
- RNA and protein synthesis mechanisms
- Immune cells in cancer
- Calpain Protease Function and Regulation
- Traumatic Ocular and Foreign Body Injuries
Peng Cheng Laboratory
2023-2025
Jinan University
2023-2025
The People's Hospital of Guangxi Zhuang Autonomous Region
2014-2024
Beijing University of Technology
2019-2024
Northwest Normal University
2024
Yangzhou University
2023-2024
Tencent (China)
2023
Nanjing Product Quality Supervision and Inspection Institute
2023
Xiamen University
2023
Army Medical University
2023
BackgroundMedical artificial intelligence (AI) has entered the clinical implementation phase, although real-world performance of deep-learning systems (DLSs) for screening fundus disease remains unsatisfactory. Our study aimed to train a clinically applicable DLS diseases using data derived from real world, and externally test model photographs collected prospectively settings in which would most likely be adopted.MethodsIn this national evidence study, we trained DLS, Comprehensive AI...
Abstract De novo peptide sequencing is a promising approach for novel discovery, highlighting the performance improvements state-of-the-art models. The quality of mass spectra often varies due to unexpected missing certain ions, presenting significant challenge in de sequencing. Here, we use concept complementary enhance ion information experimental spectrum and demonstrate it through conceptual practical analyses. Afterward, design suitable encoders encode corresponding propose model...
Background As effective medication to treat COVID-19 is currently unavailable, preventive remedies may be particularly important.
Purpose To establish and validate a universal artificial intelligence (AI) platform for collaborative management of cataracts involving multilevel clinical scenarios explored an AI-based medical referral pattern to improve efficiency resource coverage. Methods The training validation datasets were derived from the Chinese Medical Alliance Artificial Intelligence, covering healthcare facilities capture modes. labelled using three-step strategy: (1) mode recognition; (2) cataract diagnosis as...
Acute ocular hypertension (AOH) is the most important characteristic of acute glaucoma, which can lead to retinal ganglion cell (RGC) death and permanent vision loss. So far, approved effective therapy still lacking in glaucoma. PANoptosis (pyroptosis, apoptosis, necroptosis), consists three key modes programmed death-apoptosis, necroptosis, pyroptosis-may contribute AOH-induced RGC death. Previous studies have demonstrated that melatonin (N-acetyl-5-methoxytryptamine) exerts a...
Compared with proteins, DNA and RNA are more difficult languages to interpret because four-letter coded DNA/RNA sequences have less information content than 20-letter protein sequences. While BERT (Bidirectional Encoder Representations from Transformers)-like language models been developed for RNA, they ineffective at capturing the evolutionary homologous unlike conserved. Here, we an unsupervised multiple sequence alignment-based model (RNA-MSM) by utilizing automatic pipeline, RNAcmap, as...
Objective To develop and validate an artificial intelligence diagnostic system based on X-ray imaging data for diagnosing vertebral compression fractures (VCFs) Methods In total, 1904 patients who underwent at four independent hospitals were retrospectively (n=1847) prospectively (n=57) enrolled. The participants separated into a development cohort, prospective test cohort three external cohorts. proposed model used transfer learning method the ResNet-18 architecture. performance of was...
Place recognition and loop-closure detection are main challenges in the localization, mapping navigation tasks of self-driving vehicles. In this paper, we solve problem by incorporating deep-learning based point cloud description method coarse-to-fine sequence matching strategy. More specifically, propose a deep neural network to extract global descriptor from original large-scale 3D cloud, then on which, typical place analysis approach is presented investigate feature space distribution...
The aim of this study was to develop an intelligent system based on a deep learning algorithm for automatically diagnosing fungal keratitis (FK) in vivo confocal microscopy (IVCM) images.A total 2,088 IVCM images were included the training dataset. positive group consisted 688 with hyphae, and negative 1,400 without hyphae. A 535 testing dataset not Deep Residual Learning Image Recognition (ResNet) used build FK automatically. verified by external validation using area under receiver...
Abstract The objective of this study is to expound the CT features COVID-19 patients whose throat swab samples were negative for two consecutive nucleic acid tests after treatment. We retrospectively reviewed 46 with RT-PCR cases divided into moderate group and severe/critical according disease severity. Clinical scanning data collected. signs pulmonary lesions score lung involvement expounded. Thirty-nine seven included. Residual visible in images. Moderate showed peripheral while exhibited...
Medical artificial intelligence (AI) has been moving from the research phase to clinical implementation. However, most AI-based models are mainly built using high-quality images preprocessed in laboratory, which is not representative of real-world settings. This dataset bias proves a major driver AI system dysfunction. Inspired by design flow cytometry, DeepFundus, deep-learning-based fundus image classifier, developed provide automated and multidimensional sorting address this data quality...
Introduction: Recurrent pleomorphic adenoma (PA) in the submandibular gland is a rare tumor that may be misdiagnosed as an inflammatory lesion. The imaging manifestations of recurrent PA are unclear, with only three case reports reporting CT and MRI imaging, respectively. Our report first comprehensively describes gland. Case Presentation: A 28-year-old woman had right recurred 5 years after resection gradually grew larger. She no special discomfort was diagnosed recurrence adenoma. patient...
Previous data have indicated that the development of resistance to amprenavir, an inhibitor human immunodeficiency virus type 1 protease, is associated with substitution valine for isoleucine at residue 50 (I50V) in viral protease. We present further findings from retrospective genotypic and phenotypic analyses plasma samples protease inhibitor-naïve nucleoside reverse transcriptase (NRTI)-experienced patients who experienced virological failure while participating a clinical trial where...
A challenge of chronic diseases that remains to be solved is how liberate patients and medical resources from the burdens long-term monitoring periodic visits. Precise management based on artificial intelligence (AI) holds great promise; however, a clinical application fully integrates prediction telehealth computing has not been achieved, further efforts are required validate its real-world benefits. Taking congenital cataract as representative, we used Bayesian deep-learning algorithms...
Background: Artificial intelligence (AI) has great potential to detect fungal keratitis using in vivo confocal microscopy images, but its clinical value remains unclarified. A major limitation of utility is the lack explainability and interpretability. Methods: An explainable AI (XAI) system based on Gradient-weighted Class Activation Mapping (Grad-CAM) Guided Grad-CAM was established. In this randomized controlled trial, nine ophthalmologists (three expert ophthalmologists, three competent...
Purpose: Strategies for neuroprotection are the main targets of glaucoma research. The neuroprotective properties SRT2104 administration have been proven in central nervous system degeneration diseases through activation nicotinamide adenine dinucleotide-dependent deacetylase-silence information regulator 1 (Sirt1). Here, we investigated whether could protect retina from ischemia/reperfusion (I/R) injury and underlying mechanisms. Methods: was intravitreally injected immediately after I/R...
Chronic neuro-inflammation is involved in the death of retinal ganglion cells (RGCs) glaucoma. The aim this study to determine whether wogonin can suppress inflammatory responses and rescue RGCs after optic nerve crush (ONC), an ideal animal model Wogonin was administered intraperitoneally 10 min establishment ONC model. In study, treatment reduced loss inhibited apoptosis demonstrated by increased Brn3a labeling at day 14 decreased cleaved caspase-3 expression 7 ONC, respectively. model,...