Meeting Banner
Abstract #4910

Deep learning DCE-MRI parameter estimation: Application in pancreatic cancer

Tim Ottens1, Sebastiano Barbieri2, Matthew Orton3, Remy Klaassen4, Hanneke van Laarhoven4, Hans Crezee5, Aart Nederveen1, and Oliver Gurney-Champion1
1Radiology and Nuclear Medicine, Amsterdam UMC, Amsterdam, Netherlands, 2Centre for Big Data Research in Health, Sydney, Australia, 3Radiology, The Royal Marsden NHS Foundation Trust and The Institute for Cancer Research, London, United Kingdom, 4Medical Oncology, Amsterdam UMC, Amsterdam, Netherlands, 5Radiation Oncology, Amsterdam UMC, Amsterdam, Netherlands

Synopsis

Quantitative physiological perfusion parameters can be obtained from dynamic contrast-enhanced (DCE)-MRI. Conventionally, fitting is done with the non-linear least squares (NLLS) approach. However, the NLLS-fit suffers from long processing times and results in noisy parameter maps. In this work, we implemented a physics-informed gated recurrent unit (GRU) network with attention layers for estimating physiological parameters using the extended Tofts model. In simulations, we show it outperforms NLLS with more accurate and precise parameter maps. We show our method produced substantially less noisy parameter maps than NLLS in a fraction of the time in pancreatic cancer patients.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords