![Katya Blanter](https://profiles-cardiff.imgix.net/attachments/531?w=200&h=200&auto=format&crop=faces&fit=crop&q=90")
Overview
Research Summary – UHF MRI safety using machine learning tools
Images acquired using Ultra High Field MRI can contain artificial artifacts, which make it more difficult for researchers and clinicians to assess the results. This can be mitigated with a method called parallel radiofrequency transmission, but that can cause safety concerns in terms of body tissue heating (evaluated by means of a surrogate measure called specific absorptions rate, or SAR). These concerns are amplified when the patient or research participant has the propensity to move during MRI scanning. My thesis investigates ways of applying machine learning tools to mitigate this issue. The overarching purpose is to maintain the safety of patients who must undergo MRI scanning at ultra high fields, while simultaneously ensuring that this method can be used to its full potential.
Education
- BA in psychology and philosophy from Saint Louis University
- MSc in neuroimaging methods and applications from Cardiff University
Publication
2024
- Blanter, K., Plumley, A., Malik, S. and Kopanoglu, E. 2024. Estimating variations in SAR calculations due to within-scan patient motion using cGANs for parallel RF transmission at ultrahigh field MRI. Presented at: 2024 ISMRM & ISMRT Annual Meeting & Exhibition, Singapore, 4-9 May, 2024.
- Blanter, K., Plumley, A. and Kopanoglu, E. 2024. The effects of simulated SAR data processing methods and network parameter tuning on gridding artifacts and network estimation accuracy. Presented at: 2024 ISMRM & ISMRT Annual Meeting & Exhibition, Singapore, 4-9 May 2024.
2023
- Blanter, K., Plumley, A., Malik, S. and Kopanoglu, E. 2023. Towards applying deep learning to predict rigid motion-induced changes in Q-matrices from UHF-MRI pTx simulations. Presented at: 2023 ISMRM & ISMRT Annual Meeting & Exhibition, 03 - 08 June, 2023.
Cynadleddau
- Blanter, K., Plumley, A., Malik, S. and Kopanoglu, E. 2024. Estimating variations in SAR calculations due to within-scan patient motion using cGANs for parallel RF transmission at ultrahigh field MRI. Presented at: 2024 ISMRM & ISMRT Annual Meeting & Exhibition, Singapore, 4-9 May, 2024.
- Blanter, K., Plumley, A. and Kopanoglu, E. 2024. The effects of simulated SAR data processing methods and network parameter tuning on gridding artifacts and network estimation accuracy. Presented at: 2024 ISMRM & ISMRT Annual Meeting & Exhibition, Singapore, 4-9 May 2024.
- Blanter, K., Plumley, A., Malik, S. and Kopanoglu, E. 2023. Towards applying deep learning to predict rigid motion-induced changes in Q-matrices from UHF-MRI pTx simulations. Presented at: 2023 ISMRM & ISMRT Annual Meeting & Exhibition, 03 - 08 June, 2023.
Research
Thesis
Using machine learning to ensure the safety of participants who cannot remain still during magnetic resonance imaging
Images acquired using Ultra High Field MRI can contain artificial artifacts, which make it more difficult for researchers and clinicians to assess the results. This can be mitigated with a method called parallel radiofrequency transmission, but that can cause safety concerns in terms of body tissue heating (evaluated by means of a surrogate measure called specific absorptions rate, or SAR). These concerns are amplified when the patient or research participant has the propensity to move during MRI scanning. My thesis investigates ways of applying machine learning tools to mitigate this issue. The overarching purpose is to maintain the safety of patients who must undergo MRI scanning at ultra high fields, while simultaneously ensuring that this method can be used to its full potential.
Funding sources
UKRI, EPSRC
Teaching
2021 -2022 - PG tutor
Advanced HE Associate Fellow
Cardiff University Education Associate Fellow
Supervisors
Contact Details
Cardiff University Brain Research Imaging Centre, Maindy Road, Cardiff, CF24 4HQ