Using HPC tools to create 3D tissue models for visualization purposes

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27740%2F25%3A10260176" target="_blank" >RIV/61989100:27740/25:10260176 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Using HPC tools to create 3D tissue models for visualization purposes

Popis výsledku v původním jazyce

The contribution “Using HPC tools to create 3D tissue models for visualization purposes” demonstrates how High-Performance Computing (HPC) tools can be leveraged to generate realistic three-dimensional tissue models designed for visualization in Augmented Reality (AR) and Virtual Reality (VR) environments. In a collaborative effort between the National Competence Centre for HPC and Misterine s.r.o., an integrated workflow was developed to convert medical imaging data (e.g., CT or MRI) into high-quality 3D models suitable for AR/VR visualization. The process encompasses medical image processing, volume and mesh generation using deep learning and AI inference on supercomputers, and post-processing steps such as mesh optimization, texturing, and geometry simplification to ensure performance on interactive platforms.A core challenge addressed was the integration of HPC-driven computations with visualization software, ensuring both data integrity and high visual fidelity. Mesh reduction techniques, including decimation and re-meshing, were applied to produce medium-resolution models that retain essential anatomical detail while remaining efficient for rendering. Supercomputing workflows also enable slicing and cross-section visualization of tissues to reveal internal structures, providing deeper insights that can support medical training and analysis.The resulting 3D models can be exported to common formats such as FBX and used within applications like Misterine Studio &amp; App to create interactive AR/VR experiences. This approach expands possibilities for medical education, data visualization, and immersive training, allowing health professionals, students, and researchers to explore intricate biological structures without reliance on physical specimens. By employing HPC capabilities, large datasets can be processed efficiently, enabling scalable and high-quality 3D model production for a variety of visualization platforms.

Název v anglickém jazyce

Using HPC tools to create 3D tissue models for visualization purposes

Popis výsledku anglicky

The contribution “Using HPC tools to create 3D tissue models for visualization purposes” demonstrates how High-Performance Computing (HPC) tools can be leveraged to generate realistic three-dimensional tissue models designed for visualization in Augmented Reality (AR) and Virtual Reality (VR) environments. In a collaborative effort between the National Competence Centre for HPC and Misterine s.r.o., an integrated workflow was developed to convert medical imaging data (e.g., CT or MRI) into high-quality 3D models suitable for AR/VR visualization. The process encompasses medical image processing, volume and mesh generation using deep learning and AI inference on supercomputers, and post-processing steps such as mesh optimization, texturing, and geometry simplification to ensure performance on interactive platforms.A core challenge addressed was the integration of HPC-driven computations with visualization software, ensuring both data integrity and high visual fidelity. Mesh reduction techniques, including decimation and re-meshing, were applied to produce medium-resolution models that retain essential anatomical detail while remaining efficient for rendering. Supercomputing workflows also enable slicing and cross-section visualization of tissues to reveal internal structures, providing deeper insights that can support medical training and analysis.The resulting 3D models can be exported to common formats such as FBX and used within applications like Misterine Studio &amp; App to create interactive AR/VR experiences. This approach expands possibilities for medical education, data visualization, and immersive training, allowing health professionals, students, and researchers to explore intricate biological structures without reliance on physical specimens. By employing HPC capabilities, large datasets can be processed efficiently, enabling scalable and high-quality 3D model production for a variety of visualization platforms.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

20600 - Medical engineering

Projekt

—

Návaznosti

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů