Paul Sweeney

Machine learning is revolutionising healthcare due to its innate ability to isolate patterns in big data, however it is limited in specifying why these patterns exist. I am interested in using biophysical models to predict how fluid and mass is transported through cancerous tissue, and provide more informed training data to machine learning algorithms. An artificial intelligence such as this could provide reasoning behind identified patterns in tumour medical imaging data.

Brief CV

Publications

Modelling the transport of fluid through heterogeneous, whole tumours in silico.

Published to PLOS Computational Biology

P W Sweeney, A d’Esposito, S Walker-Samuel and R J Shipley, PLOS Computational Biology, 15(6): e1006751 (2019).

Computational fluid dynamics with imaging of cleared tissue and of in vivo perfusion predicts drug uptake and treatment responses in tumours.

Published to Nature Biomedical Engineering

A d’Esposito*, P W Sweeney*, M Ali, M Saleh, R Ramasawmy, T A Roberts, G Agliardi, A Desjardins, M F Lythgoe, R B Pedley, R J Shipley* and S Walker-Samuel*, Nature Biomedical Engineering, 2(10): 773-787 (2018).

Insights into cerebral haemodynamics and oxygenation utilising in vivo mural cell imaging and mathematical modelling.

Published to Scientific Reports

P W Sweeney, S Walker-Samuel and R J Shipley, Scientific Reports, 8:1373 (2018)

Best conference attended so far

International Society on Oxygen Transport to Tissue Annual Conference, July 2014