Publications by authors named "A A M Coelho Castelo"
Article Synopsis
- The study addresses the challenges faced in liver surgeries due to the complex anatomy of liver blood vessels and the limitations of traditional 2D ultrasound imaging, which is often affected by noise and artifacts.
- Researchers developed an AI-based "2D-weighted U-Net model" to improve intraoperative ultrasonography by enhancing the real-time detection and segmentation of key liver blood vessels.
- The deep learning model demonstrated high accuracy in identifying various vessels, achieving Dice scores between 0.84 and 0.96, with plans to extend its use for more comprehensive liver vascular mapping in future surgeries.
Manual delineation of liver segments on computed tomography (CT) images for primary/secondary liver cancer (LC) patients is time-intensive and prone to inter/intra-observer variability. Therefore, we developed a deep-learning-based model to auto-contour liver segments and spleen on contrast-enhanced CT (CECT) images. We trained two models using 3d patch-based attention U-Net ([Formula: see text] and 3d full resolution of nnU-Net ([Formula: see text] to determine the best architecture ([Formula: see text].
View Article and Find Full Text PDFThis work introduces a novel numerical method designed to address three-dimensional unsteady free surface flows incorporating integral viscoelastic constitutive equations, specifically the K-BKZ-PSM (Kaye-Bernstein, Kearsley, Zapas-Papanastasiou, Scriven, Macosko) model. The new proposed methodology employs a second-order finite difference approach along with the deformation fields method to solve the integral constitutive equation and the marker particle method (known as marker-and-cell) to accurately capture the evolution of the fluid's free surface. The newly developed numerical method has proven its effectiveness in handling complex fluid flow scenarios, including confined flows and extrudate swell simulations of Boger fluids.
View Article and Find Full Text PDFIntroduction: There are limited data about the outcomes of nonelective transcatheter aortic valve implantation (TAVI). Some studies suggest that these patients (pts) have worst results. Our purpose was to compare outcomes in pts submitted to urgent versus elective TAVI.
View Article and Find Full Text PDFBackground: Risk factors for stroke after transcatheter aortic valve implantation (TAVI) are currently incompletely understood.
Purpose: To identify possible predictors of early post-TAVI stroke and explore its short-term outcomes.
Methods: Retrospective analysis of consecutive patients (pts) submitted to TAVI between 2009 and 2020 in a tertiary center.