3D reconstruction of porous material based on 2D images using conditional generative adversarial neural networks (CGANs)

The School of Computing at the University of Leeds is offering a funded Ph.D. opportunity for students (international and UK-based) interested in the field of 3D image analysis and deep learning. The project aims to develop a framework for the 3D reconstruction of biological and geological porous materials, based on 2D images, using conditional generative adversarial neural networks (CGANs). Porous materials have unique properties, including porosity, permeability, surface area, and mechanical stiffness, that are related to their complex 3D structure. However, obtaining a full 3D representation of these materials can be challenging and time-consuming, making the use of computational methods like deep learning a more efficient and cost-effective approach.

The Ph.D. project will focus on the use of CGANs to reconstruct 3D images of biological and geological porous materials from 2D images. The performance of the developed framework will be evaluated using metrics such as reconstruction accuracy, computational efficiency, image quality, and physical properties. 

The ideal candidate for this Ph.D. project should hold a Master’s degree or equivalent in computer science, geoscience, mathematics, physics, biomedicine, or a related discipline. Familiarity with 3D image analysis, deep learning, and programming languages like Python or Matlab and packages such as TensorFlow or PyTorch is necessary. A motivation to learn about porous material physics or prior experience in this field is favourable.

The successful completion of this Ph.D. project is expected to have a significant impact on the study of biological and geological porous materials. The CGAN-based framework developed in this project will reduce the need for extensive and expensive 3D imaging techniques, making it applicable in areas such as medical imaging, material science, biomedicine, environmental science, and geoscience. Furthermore, the findings of the project could be used to design variations of biological tissues that can serve specific purposes or exhibit certain behaviours which can be used as input for 3D printing artificial bone tissues.