Oliver Gurney-Champion

Dr. O.J. Gurney-Champion is an Associate Professor and, together with his team of technical and clinical researchers, he develops and improves quantitative MRI (qMRI) techniques for personalizing treatment in tumour patients at Amsterdam UMC. Such qMRI imaging biomarkers allow us to assess tumour properties such as perfusion, cell density, elastic properties and oxygenation. This information helps us determine the best personalized treatment option. His group works on the development of acquisition and processing techniques (including AI-driven techniques), as well as clinical testing.

During his studies (Physics), dr. Gurney-Champion developed the technical insight and tools needed for developing new MRI techniques. In 2016, he obtained his PhD at Amsterdam UMC on “MRI of pancreatic cancer for radiotherapy purposes”, during which he became an expert on quantitative imaging and initiated the development of IVIM-DWI scanning. During his Postdoc, at the Institute of Cancer Research, a world-leading cancer research centre, he became an expert on deep learning for quantitative MRI. Since 2020, dr. Gurney-Champion is an assistant professor at Amsterdam UMC.

His research covers the full pathway from technical development to clinical implementation of quantitative MRI. One research theme focuses on developing new acquisition, reconstruction and analysis techniques, including AI-based methods, to make quantitative MRI measurements more accurate, precise and robust. A second theme focuses on translating these techniques into standardized and practical clinical tools that can work reliably across scanners and hospitals. The third theme is clinical validation, establishing whether quantitative MRI biomarkers provide meaningful information for diagnosis, treatment selection and treatment monitoring.

A particular focus of his work is making quantitative MRI more reproducible and accessible to the wider research community. Dr. Gurney-Champion has organized and chaired international meetings on quantitative MRI, AI and oncology, including the ISMRM IVIM consensus meeting. This resulted in an international consensus publication providing recommendations for IVIM imaging and analysis. He is a board member of the ISMRM open science initiative for perfusion imaging (OSIPI), where he leads the development of an open-source IVIM code repository that brings together standardized and validated implementations from the perfusion MRI community. Through these activities, he works with researchers, clinicians and industry partners to move quantitative MRI from promising research techniques towards robust, reproducible clinical tools.

Dr. Gurney-Champion teaches various classes at BSc and MSc level, to students from Physics, Biomedical Technology and Physics, and Medische Informatiekunde. He is the course coordinator and, together with Matthan Caan, the main lecturer for Deep Learning for Medical Imaging. He also lectures on the Advanced MRI, “Image Acquisition and Processing” and “Personalized Imaging” courses. As an examiner for the Physics, Biomedical Technology and Physics and Artificial Intelligence study programs, his team and he supervise BSc and MSc students throughout the year.

Team members

• (Co-)Promotor:
  • Benthe Ariëns
  • Dilara Tank
  • Daan Kuppens
  • Slava Pshenov
  • Alessandro Di Matteo
  • Jelmer Appelman
  • Federica Lupo
• Postdocs and senior researchers
  • Nienke Wassenaar
  • Myrte Wennen
  • Eric Schrauben
  • Renske Merton
• Alumni
  • Marian Troelstra
  • Victor Strijbis
  • Susi Rauh
  • Natalia Korobova
  • Wilhelm Stehling

Current projects

• NWO Open Technology: ReCreaTe: making quantitative perfusion MRI reproducible
• VIDI: Self-supervised physics-informed deep learning quantitative MRI of tumour microstructural imaging for personalized cancer treatments
• KWF-YIG: TOP-QMRI: TOwards Personalized multi-modality oesophageal cancer treatment using machine learning-based Quantitative MRI
• CCA: Non-invasive, accessible liver function assessment with quantitative MRI to guide hepatectomy in hepatic cancer
• Hanarth: The integration of deep learning for quantitative MRI in clinical and research workflows to personalize treatment of cervical and head and neck cancer
• NWO Small NWA: Minimally invasive techniques in oncology: the next steps
• CCA: ROTATION: High Resolution, respiraOry moTion compensATed, abdomInal tumOur imagiNg: Quantitative biomarkers and anatomical imaging
• TKI-PPP: Gamechanger: Development of MRI based endovasculAR procedures for Vascular surgerY (MARVY)

Selected Publications

• Gurney-Champion, O. J., Mahmood, … & Redalen, K. R. (2020). Quantitative imaging for radiotherapy purposes. Radiotherapy and Oncology, 146, 66-75.
• Gurney-Champion, O. J., Klaassen, R., … & Nederveen, A. J. (2018). Comparison of six fit algorithms for the intra-voxel incoherent motion model of diffusion-weighted magnetic resonance imaging data of pancreatic cancer patients. PloS one, 13(4), e0194590.
• Kaandorp, M. P., Barbieri, … & Gurney‐Champion, O. J. (2021). Improved unsupervised physics‐informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients. Magnetic resonance in medicine, 86(4), 2250-2265.
• Ottens, T., Barbieri, S., … & Gurney-Champion, O. J. (2022). Deep learning DCE-MRI parameter estimation: Application in pancreatic cancer. Medical image analysis, 80, 102512.
• Barbieri, S., Gurney‐Champion, O. J., Klaassen, R., & Thoeny, H. C. (2020). Deep learning how to fit an intravoxel incoherent motion model to diffusion‐weighted MRI. Magnetic resonance in medicine, 83(1), 312-321.

Software

• IVIM-NET, DCE-NET and NCDEs

Other sites

• Github
• Google Scholar‬
• Amsterdam UMC profile
• ORCiD
• ResearchGate

Keywords

• Quantitative MRI
• Oncology
• Deep learning
• Dynamic Contrast-enhanced MRI (DCE)
• Diffusion-weighted MRI (DWI)
• Intravoxel incoherent motion MRI (IVIM)
• Radiotherapy