Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10838546 | PMC |
| http://dx.doi.org/10.1038/s41587-020-00758-7 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Deep-Learning Generated Synthetic Material Decomposition Images Based on Single-Energy CT to Differentiate Intracranial Hemorrhage and Contrast Staining Within 24 Hours After Endovascular Thrombectomy.
CNS Neurosci Ther
January 2025
Department of Radiology, Affiliated Hangzhou First People's Hospital, Westlake University School of Medicine, Hangzhou, China.
Aims: To develop a transformer-based generative adversarial network (trans-GAN) that can generate synthetic material decomposition images from single-energy CT (SECT) for real-time detection of intracranial hemorrhage (ICH) after endovascular thrombectomy.
Materials: We retrospectively collected data from two hospitals, consisting of 237 dual-energy CT (DECT) scans, including matched iodine overlay maps, virtual noncontrast, and simulated SECT images. These scans were randomly divided into a training set (n = 190) and an internal validation set (n = 47) in a 4:1 ratio based on the proportion of ICH.
Discovery of sugar-based natural framework as phytopathogenic virus capsid protein inhibitors using a state-of-the-art multiple screening strategy.
Int J Biol Macromol
January 2025
State Key Laboratory of Green Pesticides, Key Laboratory of Green Pesticide and Agricultural Bioengineering, Ministry of Education, Center for R&D of Fine Chemicals of Guizhou University, Guiyang 550025, China. Electronic address:
The prompt and efficient identification of targeted inhibitors against unscrupulous pathogenic viruses holds promise for preventing epidemic disease outbreaks. Herein, a comprehensive multichannel screening method (multiple docking cross-validation, molecular dynamics simulation, and density functional theory calculation) integrated with bioactivity identification is rationally established using sugar-based natural ligand libraries to target tobacco mosaic virus (TMV) capsid proteins. Encouragingly, compounds A0 (K = 0.
View Article and Find Full Text PDFProtein-ligand binding affinity prediction using multi-instance learning with docking structures.
Front Pharmacol
January 2025
Global Security Computing Applications Division, Lawrence Livermore National Laboratory, Livermore, CA, United States.
Introduction: Recent advances in 3D structure-based deep learning approaches demonstrate improved accuracy in predicting protein-ligand binding affinity in drug discovery. These methods complement physics-based computational modeling such as molecular docking for virtual high-throughput screening. Despite recent advances and improved predictive performance, most methods in this category primarily rely on utilizing co-crystal complex structures and experimentally measured binding affinities as both input and output data for model training.
View Article and Find Full Text PDFVirtual Human Retina: Simulating Neural Signalling, Degeneration, and Responses to Electrical Stimulation.
Brain Stimul
January 2025
Graduate School of Biomedical Engineering, UNSW, Sydney, NSW 2052, Australia; Tyree Foundation Institute of Health Engineering (IHealthE), UNSW, Sydney, NSW 2052, Australia. Electronic address:
Introduction: Current brain-based visual prostheses pose significant challenges impeding adoption such as the necessarily complex surgeries and occurrence of more substantial side effects due to the sensitivity of the brain. This has led to much effort toward vision restoration being focused on the more approachable part of the brain - the retina. Here we introduce a novel, parameterized simulation platform that enables study of human retinal degeneration and optimization of stimulation strategies.
View Article and Find Full Text PDFSynthesized colonoscopy dataset from high-fidelity virtual colon with abnormal simulation.
Comput Biol Med
January 2025
State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, 150080, China. Electronic address:
With the advent of the deep learning-based colonoscopy system, the need for a vast amount of high-quality colonoscopy image datasets for training is crucial. However, the generalization ability of deep learning models is challenged by the limited availability of colonoscopy images due to regulatory restrictions and privacy concerns. In this paper, we propose a method for rendering high-fidelity 3D colon models and synthesizing diversified colonoscopy images with abnormalities such as polyps, bleeding, and ulcers, which can be used to train deep learning models.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!