Primitive Representation Learning for Unsupervised Dynamic Contrast Enhanced MRI Reconstruction
Authors: Veronika Spieker, Wenqi Huang, Cemre Ariyurek, Liam Timms, Daniel Rueckert, Onur Afacan, Julia A. Schnabel, Sila Kurugol
Organizations: Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Germany · School of Computation and Information Technology, Technical University of Munich, Germany · Department of Radiology, Boston Children’s Hospital and Harvard Medical School, USA · Munich Center for Machine Learning, Technical University of Munich, Germany · Department of Computing, Imperial College London, United Kingdom · School of Biomedical Engineering and Imaging Sciences, King’s College London, United Kingdom
Reliable quantitative analysis of dynamic contrast-enhanced MRI requires high-quality spatiotemporal reconstructions at high undersampling rates. Scan-specific reconstructions using Gaussian and Gabor primitives have shown promising results without the need for large training datasets, but have not addressed the additional dimension of dynamic contrast. We propose a multi-dimensional, primitive based framework for dynamic contrast-enhanced MRI reconstruction that disentangles the underlying anatomy, the dynamic contrast enhancement, and residual motion into separate temporal basis functions, thereby enabling a geometrical interpretation of the representation. We show that this architecture achieves performance competitive with conventional reconstruction methods, both in reconstruction quality and in the accuracy of extracted aorta and kidney enhancement curves. The modular tier design extends naturally to additional dynamic factors and higher acceleration rates. Code available at https://github.com/compai-lab/2026-GaborDCE-spieker.
Figures & tables
Figure 1: Method Overview. (A) Spatiotemporal DCE Primitive Representation consists of a contrast basis and geometry basis, modeling the primitives intensity and the primitives shape/position, respectively. (B) The weighted sum of all rendered primitives results in the DCE reconstruction time series, which is transformed into k-space to compute the unsupervised loss to the acquired data.
Figure 2: Qualitative spatial ( xy ) and spatiotemporal ( xt ) reconstruction results for an exemplary subject (kidneys/aorta on the top/bottom, respectively). While INR results in competitive but slightly noisy reconstructions compared to the conventional references, it blurs spatiotemporally (arrows). Gabor sharpens reconstructions compared to Gaussian and maintains temporal sharpness.
Figure 3
Figure 4: Gabor representation analysis. (A) Location and scale of the top-20 enhanced primitives overlaid on the reconstruction. (B) Base- and DCE-tier contrast intensity over time for the top-10% enhancing primitives; the base stays flat while the DCE tier rises at injection. (C) Learned motion-tier temporal basis (general drift, slice 05; respiratory motion, slice 12).
Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany · School of Computation and Information Technology, Technical University of Munich, Munich, Germany · Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Neuherberg, Germany +5
Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA · Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA · Department of Medicine (Cardiology), University of Minnesota, Minneapolis, MN, USA