In this work an Artificial Neural Network (ANN) was developed to help in the diagnosis of plaque vulnerability by predicting the Young modulus of the core ( ) and the plaque ( ) of atherosclerotic coronary arteries. A representative database was constructed to train the ANN using Finite Element simulations covering the ranges of mechanical properties present in the bibliography. A statistical analysis to pre-process the data and determine the most influential variables was performed to select the inputs of the ANN. The ANN was based on Multilayer Perceptron architecture and trained using the developed database, resulting in a Mean Squared Error (MSE) in the loss function under 10, enabling accurate predictions on the test dataset for and . Finally, the ANN was applied to estimate the mechanical properties of 10,000 realistic plaques, resulting in relative errors lower than 3%.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10113490 | PMC |
| http://dx.doi.org/10.3389/fphys.2023.1162436 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Construction of Supramolecular Polymer Network Elastomers Based on Pillar[5]arene/Alkyl Chain Host-Guest Interactions.
ACS Macro Lett
January 2025
Key Laboratory of Materials Chemistry for Energy Conversion and Storage, Ministry of Education, Hubei Key Laboratory of Materials Chemistry and Service Failure, Hubei Engineering Research Center for Biomaterials and Medical Protective Materials, State Key Laboratory of Materials Processing and Die & Mould Technology, School of Chemistry and Chemical Engineering, Huazhong University of Science and Technology, Wuhan 430074, China.
As a special kind of supramolecular compound with many favorable properties, pillar[]arene-based supramolecular polymer networks (SPNs) show potential application in many fields. Although we have come a long way using pillar[]arene to prepare SPNs and construct a series of smart materials, it remains a challenge to enhance the mechanical strength of pillar[]arene-based SPNs. To address this issue, a new supramolecular regulation strategy was developed, which could precisely control the preparation of pillar[]arene-based SPN materials with excellent mechanical properties by adjusting the polymer network structures.
View Article and Find Full Text PDFEOSnet: Embedded Overlap Structures for Graph Neural Networks in Predicting Material Properties.
J Phys Chem Lett
January 2025
Department of Physics, Rutgers University, Newark, New Jersey 07102, United States of America.
Graph Neural Networks (GNNs) have emerged as powerful tools for predicting material properties, yet they often struggle to capture many-body interactions and require extensive manual feature engineering. Here, we present EOSnet (Embedded Overlap Structures for Graph Neural Networks), a novel approach that addresses these limitations by incorporating Gaussian Overlap Matrix (GOM) fingerprints as node features within the GNN architecture. Unlike models that rely on explicit angular terms or human-engineered features, EOSnet efficiently encodes many-body interactions through orbital overlap matrices, providing a rotationally invariant and transferable representation of atomic environments.
View Article and Find Full Text PDFLiquid Metal Elastomer-Based U-Shaped Electrode Flexible Strain Sensors with Enhanced Stability and Sensitivity.
ACS Appl Mater Interfaces
January 2025
College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710054, China.
Soft and stretchable strain sensors are crucial for applications in human-machine interfaces, flexible robotics, and electronic skin. Among these, capacitive strain sensors are widely used and studied; however, they face challenges due to material and structural constraints, such as low baseline capacitance and susceptibility to external interference, which result in low signal-to-noise ratios and poor stability. To address these issues, we propose a U-shaped electrode flexible strain sensor based on liquid metal elastomer (LME).
View Article and Find Full Text PDFBinuclear ruthenium complex linker length tunes DNA threading intercalation kinetics.
Biophys J
January 2025
Department of Physics, Northeastern University, Boston, MA, 02115, USA. Electronic address:
Binuclear ruthenium complexes have been investigated for potential DNA-targeted therapeutic and diagnostic applications. Studies of DNA threading intercalation, in which DNA base pairs must be broken for intercalation, have revealed means of optimizing a model binuclear ruthenium complex to obtain reversible DNA-ligand assemblies with the desired properties of high affinity and slow kinetics. Here, we used single-molecule force spectroscopy to study a binuclear ruthenium complex with a longer semi-rigid linker relative to the model complex.
View Article and Find Full Text PDFFiber Bragg Grating Thermometry and Post-Treatment Ablation Size Analysis of Radiofrequency Thermal Ablation on Ex Vivo Liver, Kidney and Lung.
Sensors (Basel)
January 2025
Department of Mechanical Engineering, Politecnico di Milano, Via Giuseppe La Masa 1, 20156 Milan, Italy.
Radiofrequency ablation (RFA) is a minimally invasive procedure that utilizes localized heat to treat tumors by inducing localized tissue thermal damage. The present study aimed to evaluate the temperature evolution and spatial distribution, ablation size, and reproducibility of ablation zones in ex vivo liver, kidney, and lung using a commercial device, i.e.
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!