About this Event
Join us for the Cambridge AI in Medicine Seminar Series, hosted by the Cancer Research UK Cambridge Centre and the Department of Radiology at Addenbrooke's. This series brings together leading experts to explore cutting-edge AI applications in healthcare - from disease diagnosis to drug discovery. It's a unique opportunity for researchers, practitioners, and students to stay at the forefront of AI innovations and engage in discussions shaping the future of AI in healthcare.
This month's seminar will be held on Tuesday 26 May 2026, 12-1pm at the Jeffrey Cheah Biomedical Centre (Main Lecture Theatre), University of Cambridge and streamed online via Zoom. A light lunch from Aromi will be served from 11:45. The event will feature the following talks:
Using AI to Investigate and Correct Head Motion Bias in Structural MRI - Marta Morgado Correia, Research Professor, MRC Cognition and Brain Sciences Unit
Marta Correia is a Research Professor and Head of MRI at the MRC Cognition and Brain Sciences Unit, where she leads MRI methods research and supports multiple neuroscience programmes. She started her academic career at the University of Lisbon, researching 2D reconstruction methods for PET mammography, before moving to Cambridge in 2005 for a PhD in Diffusion MRI in the brain. Her research develops advanced MRI methods for studying brain structure and function across ageing and neurological disorders, with extensive work in diffusion MRI, high-resolution fMRI, and multi-centre data harmonisation. Marta is also actively involved in multi-site collaborative projects, teaching, and neuroscience outreach.
Abstract: Head motion during structural MRI acquisition introduces artifacts that systematically bias morphometric measurements such as cortical thickness and subcortical volume. These effects are particularly problematic in studies of ageing and neurological disease, where motion is often associated with participant group differences. This talk will go through two practical data-driven strategies for mitigating motion related bias in structural MRI analysis. First, image quality metrics, including a deep learning-based motion score, are assessed as nuisance covariates in downstream statistical modelling across multiple datasets. Second, a retrospective k-space motion correction framework is implemented using a deep learning-based test-time-training method (Motion TTT). Results demonstrate that both statistical modelling and retrospective correction substantially improve cortical thickness analyses, with retrospective correction additionally recovering heavily corrupted scans that would otherwise fail processing. Together, these approaches provide complementary solutions for improving the robustness and reliability of structural MRI morphometry in clinical and research settings.
Hypergraph Learning for Multimodal Brain Disease Analysis - Zhongying Deng, Research Associate, Department of Radiology, University of Cambridge
Zhongying Deng is a postdoctoral research associate at the Department of Radiology, University of Cambridge. His research focuses on deep learning, computer vision, and medical image analysis. He has authored over thirty peer-reviewed publications in leading journals and conferences. He serves as a reviewer for top-tier venues including IEEE T-PAMI, IEEE T-IP, IJCV, CVPR, ICCV, AAAI, and MICCAI. He also co-chaired the International Workshop on Foundation Models for General Medical AI at MICCAI 2023-2026.
Abstract: Brain diseases such as Alzheimer’s disease pose significant challenges due to their clinical complexity and far-reaching societal impact. Although recent advances in brain disease analysis have shown promise—particularly through the use of multimodal data that integrates structural and functional imaging with clinical and demographic information, effectively modelling this heterogeneous data remains a major obstacle. Hypergraphs offer a powerful solution by extending traditional graph structures to capture higher-order relationships across multiple data modalities, including MRI, PET, and non-imaging features. This talk will begin with an introduction to the fundamental concepts and properties of hypergraphs, followed by a presentation of novel hypergraph-based frameworks specifically designed to advance multimodal brain disease analysis.
This is a hybrid event so you can also join via Zoom:
https://zoom.us/j/99050467573?pwd=UE5OdFdTSFdZeUtIcU1DbXpmdlNGZz09
Meeting ID: 990 5046 7573 and Passcode: 617729
We look forward to your participation! If you are interested in getting involved and presenting your work, please email Ines Machado at [email protected]
For more information about this seminar series, see: https://www.integratedcancermedicine.org/research/cambridge-medai-seminar-series/
Event Venue & Nearby Stays
Jeffrey Cheah Biomedical Centre, Main Lecture Theatre, Puddicombe Way, Cambridge, United Kingdom
GBP 0.00
