Session Overview |
Session | |||||||||||||
Poster session II: AI / Data-driven modeling in biomechanics
| |||||||||||||
Presentations | |||||||||||||
ID: 912
BONE REMODELLING WITH ARTIFICIAL NEURAL NETWORKS 1INEGI - Institute of Science and Innovation in Mechanical and Industrial Engineering, Portugal; 2FEUP - Faculty of Engineering, University of Porto; 3ISEP - School of Engineering, Polytechnic of Porto
ID: 569
OPTIMIZATION AND INDUSTRIALIZATION OF A METABOLIC HOLTER DEVICE AND SOFTWARE DEVELOPMENT 1BEAMS Department (Bio Electro and Mechanical Systems), École Polytechnique de Bruxelles, Université Libre de Bruxelles, Brussel, Belgium; 2Heart Rhythm Management Centre, Universitair Ziekenhuis Brussel–Vrije Universiteit Brussel, Brussel, Belgium; 3Galascreen Laboratories, University of Calabria, Rende, Italy
ID: 178
DEEP LEARNING APPROACH FOR IN-STENT RESTENOSIS USING BIOLOGICALLY-INFORMED NEURAL NETWORKS Institute of Applied Mechanics, RWTH Aachen University, Germany
ID: 355
PRE-TRAINING VARIED VASCULAR GEOMETRIES WITH A DEEP LEARNING SIDE NETWORK IN PHYSICS-INFORMED NEURAL NETWORK SIMULATIONS OF VASCULAR FLUID DYNAMICS Department of Bioengineering, Imperial College London, United Kingdom
ID: 891
2D-UNET BASED APPROACH FOR 3D SEGMENTATION OF CORONARY ARTERY FROM COMPUTED TOMOGRAPHY ANGIOGRAPHY 1Politecnico di Milano, Italy; 2Centro Cardiologico Monzino, Italy
ID: 356
CFD-BASED SYNTHETIC DATA GENERATION FOR MACHINE LEARNING BASED PRESSURE DROP ASSESSMENT IN AORTIC STENOSIS 1Transilvania University of Brasov, Romania; 2Siemens SRL, Romania
ID: 281
SINE-BASED ACTIVATION FUNCTION IS SUPERIOR IN PHYSICS-INFORMED NEURAL NETWORK FOR CARDIOVASCULAR FLOWS Department Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada
ID: 376
THREE-DIMENSIONAL FLOW RECONSTRUCTION IN A DISSECTED AORTA FROM 4D-MRI DATA 1Department of Aeronautics, Imperial College London, United Kingdom; 2Department of Mechanical Engineering, University College London, United Kingdom; 3Wellcome-EPSRC Centre for Interventional Surgical Sciences, London, United Kingdom; 4Department of Diagnostic, Interventional and Pediatric Radiology, Inselspital, Bern, Switzerland.; 5Clinic of Vascular Surgery, Inselspital, University of Bern, Switzerland; 6Centre for Translational Cardiovascular Imaging, University College London, United Kingdom
ID: 699
THE HARD REALITY OF SCATTERED DATA TO PREDICT HEART RHYTHM DISORDERS 1Department of Biomedical Engineering, Eindhoven University of Technology, the Netherlands; 2Department of Cardiology, Catharina Hospital Eindhoven, the Netherlands; 3Department of Biomedical Engineering, CARIM School for Cardiovascular Diseases, Maastricht University, the Netherlands
ID: 911
REVERSE HOMOGENIZATION USING NEURAL NETWORKS FOR STRESS SHIELDING MINIMIZATION 1INEGI - Institute of Science and Innovation in Mechanical and Industrial Engineering, Portugal; 2FEUP - Faculty of Engineering, University of Porto; 3ISEP - School of Engineering, Polytechnic of Porto
ID: 654
PARAMETER FITTING FOR A VISCOELASTIC CONSTITUTIVE MODEL USING A MACHINE LEARNING MODEL 1Universidad de Santiago de Chile, Chile; 2Pontificia Universidad Católica de Chile, Chile; 3Universidad de Chile, Chile
|