SAVE the DATE: Rhinodiagnost Final Symposium

The Rhinodiagnost final symposium is over, but if you click here you can read the individual presentations. The final symposium of Rhinodiagnost on 9 December 2020 will give our cooperation partners and research colleagues an overview of the results. We invite you to an inspiring afternoon of online presentations and discussions. Further details on the event, registration and the presentations […]

» Read more

Containers for Rhinodiagnost

The Rhinodiagnost article “Web-access to HPC for Rhinodiagnost” presents reasons and efforts that led to the use of Jupyter as a multi-functional web interface for easy access to HPC resources in the Rhinodiagnost project. In order to use Jupyter in the project outside the HPC environment or without the necessity of an HPC clusters, the solution is transferred into self-sufficient […]

» Read more

Web-access to HPC for Rhinodiagnost

Easy access and integration of external users and workflow managers to the HPC resources is crucial for the Rhinodiagnostic project. Therefore, the Jülich Supercomputing Centre (JSC) as part of the Forschungszentrum Jülich added a web access based on Jupyter/JupyterHub to the usual access via SSH. Jupyter (https://jupyter.org) is an open source web application and offers (in combination with JupyterHub) an […]

» Read more

RWTH Aachen University prints 3D model of nasal cavity

The Rhinodiagnost team, the profile section Computational Science and Engineering (CompSE) of RWTH Aachen University, and the Jülich Aachen Research Alliance – High-Performance Computing (JARA-HPC) jointly participated in the “RWTH Science Night” and printed a 2:1 computer tomography-based 3D model of a nasal cavity. Therefore, a fused-deposition modeling (FDM) method was used to print the object layer-wise. The printing instructions […]

» Read more

Artificial Intelligence in Rhinodiagnost

Problem definition: Segmentation (generation of content-related regions, here: determination of nasal cavities and paranasal sinuses from CT images) using a “Convolutional Neural Network” (CNN) with Google TensorFlow In order to generate a 3D model from image data, the pixels that should represent the 3D model are to be selected. But CT pictures have image noise (random variation of brightness or […]

» Read more

IraSME Project “Rhinodiagnost”

A meaningful rhinological diagnosis is key to evaluate the eff ectiveness of the patient-speci fic nasal functionalities, taking into account the respective pathology. The diagnostic quality is currently primarily based on the quality of the training of the practicing physician and his or her experience in the treatment of speci fic clinical pictures. Unfortunately, such analyses do not include any information on the […]

» Read more

Video – Flow

  Computational fluid dynamics (CFD) is an established method for the simulation of complex flows. It solves the Navier-Stokes equations (momentum, mass, and energy conservation) with numerical methods (e.g. finite volume of lattice-Bolztmann methods). Flow-related problems are processed in four steps. First, a geometry covering the volume of interest is created in a CAD program. The geometry is then cross-linked […]

» Read more

3D View

Image files that have been created by magnetic resonance tomography (MR), computed tomography (CT) or microtomography can be converted into a computer model by image-based meshing. With the Marching Cubes algorithm, a voxel image consisting of image points is approximated by a polygon image. By using triangulation the surface is then divided into pieces that are relevant for the flow […]

» Read more