ESBiomech25 Congress in Zurich

PhD Studentship in Data-driven image mechanics (D2IM): a deep learning approach to predict displacement and strain fields in biological tissues from X-ray tomography @University of Greenwich

The recent advent of deep learning (DL) has enabled data-driven models, paving the way for the full exploitation of rich image datasets from which physics can be learnt. Here at the University of Greenwich we recently developed a novel data-driven image mechanics (D2IM) approach that learns from digital volume correlation (DVC) displacement fields of bone, predicting displacement and strain fields for undeformed X-ray computed tomography (XCT) images [1]. This was the first study using experimental full-field measurements on bone structures from DVC to inform DL-based model such as D2IM, which represents a major contribution in the prediction of displacement and strain fields only based on the greyscale content of undeformed XCT images. The proposed PhD project will expand on this work to further develop D2IM capability by incorporating a range of biological structures (hard and soft tissues) and loading scenarios for accurate prediction of physical fields.

The project will benefit from a unique InCiTe 3D X-ray microscope from our partner KA Imaging (https://www.kaimaging.com/industry-and-research-solutions/incite-micro-ct/) capable of sub-micron resolution and fast phase-contrast (first and only technology of this type in Europe), including in situ mechanics and dedicated software solutions available at the Centre for Advanced Materials and Manufacturing (CAMM) as well as the Centre for Advanced Simulation and Modelling (CASM).

The PhD candidate will be involved in the following work:

  1. Development of XCT protocols on the InCiTe 3D X-ray microscope including phase retrieval for in situ mechanics and DVC of hard and soft tissues.
  2. Development of novel DL strategies to enhance D2IM capability for a comprehensive prediction of displacement and strain fields in biological tissues, only based on the greyscale content of undeformed XCT images.
  3. Data analysis and dissemination. Data obtained from this project will be disseminated in high-impact journal papers and international conferences.

[1] Soar and Tozzi, 2023. Data-driven image mechanics (D2IM): a deep learning approach to predict displacement and strain fields from undeformed X-ray tomography images – Evaluation of bone mechanics. https://www.biorxiv.org/content/10.1101/2023.09.21.558878v1

More information: https://www.jobs.ac.uk/job/DDK308/phd-studentship-in-data-driven-image-mechanics-d2im-a-deep-learning-approach-to-predict-displacement-and-strain-fields-in-biological-tissues-from-x-ray-tomography


Corporate members of the ESB:

AMTI force and motion logo
BERTEC logo
Beta CAE logo
BoB Biomechanics logo
Materialise logo
Nobel Biocare logo