Implementation of Principal Component Analysis (PCA)/Singular Value Decomposition (SVD) and Neural Networks in Constructing a Reduced-Order Model for Virtual Sensing of Mechanical Stress.

This study presents the design and validation of a numerical method based on an AI-driven ROM framework for implementing stress virtual sensing. By leveraging Reduced-Order Models (ROMs), the research aims to develop a virtual stress transducer capable of the real-time monitoring of mechanical stresses in mechanical components previously analyzed with high-resolution FEM simulations under a wide range of multiple load scenarios. The ROM is constructed through neural networks trained on Finite Element Method (FEM) outputs from multiple scenarios, resulting in a simplified yet highly accurate model that can be easily implemented digitally.

The impact of the EVLP on the lung microbiome and its inflammatory reaction.

The pulmonary microbiome has emerged as a significant factor in respiratory health and diseases. Despite the sterile conditions maintained during lung perfusion (EVLP), the use of antibiotics in the perfuse liquid can lead to dynamic changes in the lung microbiome. Here, we present the design of a study that aims to investigate the hypothesis that EVLP alters the lung microbiome and induces tissue inflammation.

Combining different metal artifact reduction levels with sharpening filters and slice thickness for the visualization of mandibular canals perforated by implants.

Objectives: To investigate the influence of combining levels of metal artifact reduction (MAR) tool with different filters and slice-thickness in the detection of mandibular canals perforated by implants on CBCT scans and to objectively assess the impact of the aforementioned combinations.

Materials And Methods: Implants were placed above (8 implants) and inside (10 implants) mandibular canals of dried-mandibles. CBCT scans were obtained with the Eagle 3D unit (85 kVp, 8 mA, 5 × 5 cm FOV, 130 μm voxel size, and off/medium/high MAR levels).