Machine learning aided bioimpedance spectral imaging for tissue engineering

Cell culture using 3-D models has become increasingly prevailing in cancer research, tissue engineering and regenerative medicine. In contrast to 2-D cell culture, 3-D cell culture demonstrates enhanced cell biological activities which is more biologically relevant to the real complex in vivo conditions of living organisms. Current biochemical assays, originally designed to perform for 2-D cell monolayer samples, do show a marked difference in average cell metabolic drug response between 2-D and 3-D, and poorly represent the 3-D spheroid layered microstructure as they are generally destructive and/or capture only a fraction of the sample. As a result, non-destructive, real-time 3-D imaging technique with good temporal-spatial resolution is very desirable for the study of biological behaviour and to perform long-term monitoring of cellular dynamics, such as cell-cell interactions, proliferation, ECM deposition and drug penetration.

This PhD project aims to develop an innovative 3-D imaging & data analysing platform based on multi-frequency bioimpedance tomography and machine learning methods, to extract spectroscopic electrical properties of 3-D cultivated cells non-destructively and robustly under in vivo conditions. Objectives of this PhD project include:

  1. Design and optimise miniature bioimpedance sensors for robust 3-D cellular imaging.
  2. Investigate efficient and robust 3-D inversion algorithms with emphasis on the temporal features of the time-series tomographic images.
  3. Explore machine learning based data analysis techniques, e.g. Deep Neural Networks and Bayesian Learning, to significantly improve the measurement accuracy.
  4. Develop an integrated data/image processing and analysing platform to seamless integrate data analytics with the bioimpedance sensing system, and provide information directly related to biomedical process characterisation.
  5. Perform substantial experimental validations of the developed methods.

Successful applicant will work closely with the researchers from the Agile Tomography Group at the School of Engineering, the Bayes Centre, and the MRC Centre for Regenerative Medicine at the University of Edinburgh, to deliver high-quality interdisciplinary research and make impact on this research area.

Closing Date: 

Tuesday, July 30, 2019
Engineering School Logo
Engineering School Logo

Principal Supervisor: 

Assistant Supervisor: 

Dr Pierre Bagnaninchi, Dr Jiabin Jia

Eligibility: 

Minimum entry qualification - an Honours degree at 2:1 or above (or International equivalent) in a relevant science or engineering discipline, possibly supported by an MSc Degree. Enthusiastic and self-motivated candidates are sought with a background in sensing and signal processing.

Further information on English language requirements for EU/Overseas applicants.

Funding: 

Tuition fees and stipend are available for Home/EU students (International students can apply, but the funding only covers the Home/EU fee rate).

Further information and other funding options.

Informal Enquiries: