• Mackay, Benita

Abstract

With an approximate annual cost of £1.7 billion for the NHS, osteoporosis and osteoarthritisalone represent a major socio-economic burden to the UK. While bisphonates and nonopioids such as non-steroidal anti-inflammatory drugs are prescribed for osteoporosis, thesetypes of drugs may lead to serious medical complications when high doses are taken for along time or when someone is at an advanced age or in poor health, and may even acceleratecartilage destruction in osteoarthritis. Tissue engineering is a successful alternative oradditional approach, but the use of grafts and implants is not without risk, specifically the riskof rejection and failure. Therefore, there is a growing need for innovative techniques topromote implant integration and reduce the failure rate of osteopathic intervention.Additionally, at the other end of the age scale, poor placental function can compromise fetaldevelopment and placental function directly determines fetal growth. Poor fetal growth islinked with higher chronic disease rates, so leads to an increased probability of healthconditions in later life.The interaction between fibroblasts, pericytes, and endothelial cells in placenta can improveunderstanding of how cell placement and behaviour affect placental health. To model andanalyse these complex interactions, 3D visualisation is required, and 3D-labelling is thereforea necessity to the medical imaging field, which can take months of researcher-time. Similarly,the experimentation required in tissue engineer, from in-vitro to ex-vitro, can be equally lengthyand complex, as cell response to biochemical and biophysical cues remains poorly understood.The three areas of research in this project include labelling cells for 3D visualisation, modellingcell response to biophysical cues, and predicting biocompatibility of tissue engineeringscaffolds. The data used for these approaches includes 3D nanoscale-resolution images ofplacenta for labelling and images of 3D bioengineered scaffolds for biocompatibility analysis,which were provided by collaborators. Data also included images of stem cells cultured ontopographically-varied surfaces, to analyse stem cell response to biophysical cues, which wascollected for this project. This data was used to train multiple deep neural networks, with thegoal of applying deep learning to label cells in placenta, and both model and predict cellresponses to biophysical and biochemical cues.It was found that deep neural networks can be used to replace labour-intensive manuallabelling, with automated labels comparable, pixel-to-pixel, to manual labels by over 98% onaverage. The response of cells to physical cues can also be modelled by a deep neural network.With a probability of 𝑃 < 0.001, it can therefore be used as a model, with potential implicationsfor tissue structure development and tissue engineering. Deep learning can also be used topredict biocompatibility, which may act as a future replacement for animal models in place oftraditional computer modelling. When predictions were compared with experimental results,images displayed excellent agreement.Tissue engineering is an increasingly important area of regenerative medicine, partly due toaging populations around the world, combining cell biology, bioengineering and clinicalresearch. However, focus on health from much earlier in life, such as through analysis onplacental tissue, may also aid in overcoming the high chronic-disease levels in old age.Applying deep learning to regenerative medicine research may not only help increaseefficiency of 3D-image processing, but also potentially help increase understanding of stemcell behaviour and reduce levels of necessary animal testing in research. In the future,application of deep learning to regenerative medicine could help increase quality of life in ourlater years.

Topics

• impedance spectroscopy
• surface
• biocompatibility