
Dr Rhodri Smith
Head of PET Physics
- smithr50@cardiff.ac.uk
- +44 (0)29 2184 7683
- Wales Research and Diagnostic PET Imaging Centre, Prif Adeilad yr Ysbyty, Ysbyty Athrofaol Cymru, Parc y Mynydd Bychan, Caerdydd, CF14 4XN
- Ar gael fel goruchwyliwr ôl-raddedig
Trosolwg
Dr Smith is a state registered Clinical Scientist specialising in Nuclear Medicine and Positron Emission Tomography. Dr Smith joined PETIC in 2017 to take up the post of Head of PET Physics.
In 2016, Dr Smith completed a PhD with the University of Surrey his thesis on "Motion Correction in Medical Imaging" developed novel algorithms using artifical intelligence to enhance the quantitative and qualitative accuracy of medical images obsfucated my respiratory motion.
Dr Smith's research focus remains in developing AI solutions to enhance PET image accuracy and the implementation of novel state of the art technology to PET development
Cyhoeddiadau
2023
- Alsyed, E., Smith, R., Bartley, L., Marshall, C. and Spezi, E. 2023. A heterogeneous phantom study for investigating the stability of PET images radiomic features with varying reconstruction settings. Frontiers in Nuclear Medicine 3 (10.3389/fnume.2023.1078536)
2021
- Alsyed, E., Smith, R., Paisey, S., Marshall, C. and Spezi, E. 2021. A self organizing map for exploratory analysis of PET radiomic features. Presented at: 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), Boston, MA, USA, 31 October -7 November 20202020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC). IEEE, (10.1109/NSS/MIC42677.2020.9507846)
- Smith, R. L., Chandler, H., Alsyed, E., Bartley, L., Fielding, P. and Marshall, C. 2021. Deep learning PET epilepsy detection with a novel symmetric loss convolutional autoencoder. Presented at: 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), Boston, MA, USA, 31 October -7 November 20202020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC). IEEE pp. 1-3., (10.1109/NSS/MIC42677.2020.9507980)
2019
- Alsyed, E., Smith, R., Marshall, C., Paisey, S. and Spezi, E. 2019. The statistical influence of imaging time and segmentation volume on PET radiomic features: A preclinical study. Presented at: 2019 IEEE NSS-MIC, 26 October - 2 November 20192019 IEEE NSS-MIC. IEEE
- Smith, R., Dasari, P., Lindsay, C., King, M. and Wells, K. 2019. Dense motion propagation from sparse samples. Physics in Medicine and Biology 64(20), article number: 205023. (10.1088/1361-6560/ab41a0)
- Ackerley, I. et al. 2019. Using deep learning to detect esophageal lesions in PET-CT scans. Presented at: SPIE Medical Imaging 2019, San Diego, California, USA, 16-21 February 2019 Presented at Gimi, B. and Krol, A. eds.Proc. SPIE 10953, Medical Imaging 2019: Biomedical Applications in Molecular, Structural, and Functional Imaging. SPIE, (10.1117/12.2511738)
- Smith, R. L., Ackerley, I. M., Wells, K., Bartley, L., Paisey, S. and Marshall, C. 2019. Reinforcement learning for object detection in PET imaging. Presented at: 2019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), Manchester, England, 26 October - 02 November 20192019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC). IEEE pp. 1-4., (10.1109/NSS/MIC42101.2019.9060031)
- Ackerley, I. et al. 2019. Can deep learning detect esophageal lesions in PET-CT scans?. Presented at: 2019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), Manchester, England, 26 October - 02 November 20192019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC). IEEE pp. 1-4., (10.1109/NSS/MIC42101.2019.9059833)
2018
- Smith, R., Rahni, A., Jones, J. and Wells, K. 2018. A Kalman-based approach with EM optimization for respiratory motion modelling in medical imaging. IEEE Transactions on Radiation and Plasma Medical Sciences 3(4), pp. 410-420. (10.1109/TRPMS.2018.2879441)
- Martins, C. et al. 2018. HER3-mediated resistance to Hsp90 inhibition detected in breast cancer xenografts by affibody-based PET imaging. Clinical Cancer Research 24(8), pp. 1853--1865. (10.1158/1078-0432.CCR-17-2754)
- Smith, R. L., Paisey, S. J., Evans, N., Florence, V., Fittock, E., Siebzehnrubl, F. and Marshall, C. 2018. Deep learning pre-clinical medical image segmentation for automated organ-wise delineation of PET. Presented at: Annual Congress of the European Association of Nuclear Medicine, Barcelona, Spain, 12-16 October 2019, Vol. 45.
2017
- Smith, R. 2017. Motion correction in medical imaging. PhD Thesis, University of Surrey.
2016
- Smith, R. L., Dasari, P., Lindsay, C., King, M. and Wells, K. 2016. Dense motion propogation from sparse samples for free breathing respiratory motion modelling. Presented at: 2014 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), Seattle, WA, USA, 8-15 November 20142014 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC). IEEE pp. 1--5., (10.1109/NSSMIC.2014.7430843)
- Burley, T. A. et al. 2016. Imaging EGFR in head and neck cancer: useful prognostic and treatment monitoring tool? [Conference Abstract]. European Journal of Nuclear Medicine and Molecular Imaging 43, pp. S231--S231.
2014
- Smith, R., Rahni, A., Jones, J., Tahavori, F. and Wells, K. 2014. Motion estimation for nuclear medicine: a probabilistic approach. Presented at: SPIE Medical Imaging, San Diego, CA, USA, 15-20 February 2014 Presented at Ourselin, S. and Styner, M. A. eds.Proceedings Volume 9034, Medical Imaging 2014: Image Processing. SPIE, (10.1117/12.2044141)
2013
- Rahni, A. A. A., Smith, R., Lewis, E. and Wells, K. 2013. Extracting respiratory motion from 4D MRI using organ-wise registration. Presented at: SPIE Medical Imaging, Lake Buena Vista, FL, USA, 9-14 February 2013 Presented at Ourselin, S. and Haynor, D. R. eds.Proceedings Volume 8669, Medical Imaging 2013: Image Processing. SPIE pp. 866930., (10.1117/12.2006861)
- Smith, R. L., Rahni, A. A., Jones, J. and Wells, K. 2013. Adaptive recursive Bayesian estimation using expectation maximization for respiratory motion correction in Nuclear Medicine. Presented at: 2013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC), Seoul, South Korea, 27 October-2 November 20132013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC). IEEE pp. 1--4., (10.1109/NSSMIC.2013.6829066)
- Smith, R. L., Wells, K., Jones, J., Dasari, P., Lindsay, C. and King, M. 2013. Toward a framework for high resolution parametric respiratory motion modelling. Presented at: 2013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC), Seoul, South Korea, 27 October-2 November 20132013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC). IEEE pp. 1--4., (10.1109/NSSMIC.2013.6829294)
- Smith, R., Rahni, A. A., Jones, J. and Wells, K. 2013. Recursive Bayesian estimation for respiratory motion correction in nuclear medicine imaging. Presented at: 2012 IEEE Nuclear Science Symposium and Medical Imaging Conference, Anaheim, CA, USA, 27 Oct - 3 Nov 20122012 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC). IEEE, (10.1109/NSSMIC.2012.6551672)
Addysgu
Senior Lecturer:
Swansea University: MSc Medical Imaging
Cardiff University: BSc Digital Medical Imaging (Deputy Module Organiser)
Supervision
I am interested in supervising PhD students in the areas of:
- Advanced Medical Image Processing / Correction / Quantification
- Radiation Protection
- Positron Emission Tomography (PET)
Past projects
Past
Primary Supervisor: Joseph Penning (2021 MPhys): "Generative Adversarial Network “Steerability” for Brain PET Image Generation"
Primary Supervisor: Robert John (2021 MPhys): "Quantitative Evaluation of Synthesized Brain PET Using a Variational Autoencoder"
Primary Supervisor: Misha Pindoria (2021 Bsc): "Automated Processing for Pre-Clinical Myocardial Perfusion PET Imaging"
Present
Co-Supervisor: Khamael Al-Battat: "Radiogenomics in Lung Cancer"
Co-Supervisor: Emad Alsyed: "Clinical Utility of Radiomics in PET Imaging"
External Co-Supervisor (CVSSP University of Surrey): Ian Ackerly: "Using Deep Learning to Detect Oesophageal Lesions in PET-CT"