Project assistant - Doctoral candidate (m/f/d) University of Graz Graz, Austria PhD position 2 [...]

Euro Math Soc; Graz; On-site; EUR 30,000 - 40,000; Full time

Job summary

A leading academic institution in Austria is seeking a PhD student to join the Young Research Group focused on cardiac modeling. The project, funded by BioTechMed-Graz, aims to develop methodologies for subject-specific calibration of cardiac electromechanical models. Successful candidates should have a strong background in applied mathematics, physics, or engineering, and experience with machine learning. Responsibilities include extending inverse problem methods and integrating clinical data. This position offers a unique opportunity to contribute to innovative research in cardiovascular function.

Qualifications

• Strong background in applied mathematics or physics.
• Experience with computational modeling or machine learning.
• Knowledge of cardiovascular function and biophysical parameters.

Responsibilities

• Extend the inverse problem method to accurately model cardiovascular function.
• Integrate real clinical data for assessment.
• Apply methodology to evaluate cardiac tissue scars.

Skills

Computational modeling

Physics-informed machine learning

Inverse problem methodology

Education

Master's degree in applied mathematics, physics, or related field

Job description

Overview

Classification: applied mathematics, physics, computer science, engineering

The Young Research Group (YRG) ''CARDIOPHYDAT: CARDIOvascular PHYsics and DATa integration for digital twins" at the Department of Mathematics and Scientific Computing of the University of Graz -- funded by BioTechMed-Graz -- invites applications for one PhD student in the field of computational modeling of human cardiac function. The goal of this project is to develop novel core methodologies for the accurate subject-specific calibration of cardiac electromechanical (EM) models from clinical data. In particular, efficient and robust personalised cardiac digital twins based on physics-informed machine learning methodologies will be generated to estimate the local distribution of patient-specific biophysical and mechanical properties and infer crucial clinical biomarkers using in vivo clinical measurements.

Project focus

In the context of this project, the PhD thesis will focus on: The extension of the inverse problem method [1,2] to biophysically accurate EM models of cardiovascular function, to simultaneously determine constant and spatially heterogeneous biophysical parameters, e.g., passive and active stress parameters. The integration of real clinical data in the inverse problem methodology and the employment of the proposed methodology for the assessment of scars in the cardiac tissue using displacement data retrieved from Cine CMR sequences.

• Extend the inverse problem method to biophysically accurate EM models of cardiovascular function to determine constant and spatially heterogeneous biophysical parameters (e.g., passive and active stress parameters).
• Integrate real clinical data into the inverse problem methodology.
• Apply the methodology to assess scars in cardiac tissue using displacement data from Cine CMR sequences.