$\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning

no code implementations • 23 Apr 2024 • Kerstin Kläser, Błażej Banaszewski, Samuel Maddrell-Mander, Callum McLean, Luis Müller, Ali Parviz, Shenyang Huang, Andrew Fitzgibbon

In this work, we propose $\texttt{MiniMol}$, a foundational model for molecular learning with 10 million parameters.

Combining multimodal information for Metal Artefact Reduction: An unsupervised deep learning framework

no code implementations • 20 Apr 2020 • Marta B. M. Ranzini, Irme Groothuis, Kerstin Kläser, M. Jorge Cardoso, Johann Henckel, Sébastien Ourselin, Alister Hart, Marc Modat

Metal artefact reduction (MAR) techniques aim at removing metal-induced noise from clinical images.

Computed Tomography (CT)

Improved MR to CT synthesis for PET/MR attenuation correction using Imitation Learning

no code implementations • 21 Aug 2019 • Kerstin Kläser, Thomas Varsavsky, Pawel Markiewicz, Tom Vercauteren, David Atkinson, Kris Thielemans, Brian Hutton, M. Jorge Cardoso, Sebastien Ourselin

Quantitative results show that the network generates pCTs that seem less accurate when evaluating the Mean Absolute Error on the pCT (69. 68HU) compared to a baseline CNN (66. 25HU), but lead to significant improvement in the PET reconstruction - 115a. u.

Imitation Learning

Deep Boosted Regression for MR to CT Synthesis

no code implementations • 22 Aug 2018 • Kerstin Kläser, Pawel Markiewicz, Marta Ranzini, Wenqi Li, Marc Modat, Brian F. Hutton, David Atkinson, Kris Thielemans, M. Jorge Cardoso, Sebastien Ourselin

Attenuation correction is an essential requirement of positron emission tomography (PET) image reconstruction to allow for accurate quantification.

Computed Tomography (CT) Image Reconstruction +1