Cian Scannell is an assistant professor in the Department of Biomedical Engineering, where he works in the Medical Image Analysis (IMAG/e) group. His research topic is automated medical image analysis, primarily using deep learning. He has a particular interest in the analysis of cardiac MRI data and extensive experience in quantitative myocardial perfusion. Looking forward, he aims to bridge the gap between the development of automated image analysis tools and their deployment in the clinic. To achieve this goal, he will focus on developing models that are more generalisable and robust to data from different domains, such as different hospitals and scanners. He will also aim to improve reliability by incorporating domain knowledge such as the relevant physics and anatomy/physiology, and developing quality assurance steps.
Radiologists are often overworked and under pressure, and thus they could look at the same scans twice and come up with different interpretations. We aim to improve this using artificial intelligence for automatic and quantitative image analysis.
Cian Scannell studied Mathematical Sciences at University College Cork (Ireland) where he graduated with first-class honours in 2016. He then moved to King’s College London to undertake his master's and PhD degrees as part of the Centre for Doctoral Training in Medical Imaging. Here, he worked in close collaboration with St Thomas’ Hospital and the industrial partners, Philips Healthcare. In 2021, he received his PhD and then continued for a further year as a postdoctoral researcher funded by the Wellcome/EPRSC Centre for Medical Engineering at King’s College London with a project on the development of robust and generalisable models for clinical integration. In 2022, he was appointed assistant professor with the Medical Image Analysis group in the Department of Biomedical Engineering.
AI-AIF: artificial intelligence-based arterial input function for quantitative stress perfusion cardiac magnetic resonanceEuropean Heart Journal - Digital Health (2023)
Optimized automated cardiac MR scar quantification with GAN-based data augmentationComputer Methods and Programs in Biomedicine (2022)
High-Resolution Free-Breathing Quantitative First-Pass Perfusion Cardiac MR Using Dual-Echo Dixon With Spatio-Temporal AccelerationFrontiers in Cardiovascular Medicine (2022)
Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data(2022)
Multi-Centre, Multi-Vendor and Multi-Disease Cardiac SegmentationIEEE Transactions on Medical Imaging (2021)
Current Educational Activities
No ancillary activities