End-to-End Co-Optimization of Adaptive $k$-space Sampling and Reconstruction for Dynamic MRI

George Yiasemis, Jan-Jakob Sonke, Jonas Teuwen
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:1285-1324, 2026.

Abstract

Accelerating dynamic MRI is essential for advancing clinical imaging and improving patient comfort. Most deep learning methods for dynamic MRI reconstruction rely on predetermined or random subsampling patterns that are uniformly applied across all temporal frames. Such strategies ignore temporal correlations and fail to optimize sampling for individual cases. To address this, we propose E2E-ADS-Recon, an end-to-end framework for adaptive dynamic MRI subsampling and reconstruction. The framework integrates an Adaptive Dynamic Sampler (ADS), which generates case-specific sampling patterns for a given acceleration factor, with a dynamic MRI reconstruction network that reconstructs the adaptively sampled data into a dynamic image sequence. The ADS can produce either frame-specific or unified patterns across time frames. We evaluate the method on multi-coil cardiac cine MRI data under both 1D and 2D sampling settings and compare it with standard and optimized non-adaptive baselines. E2E-ADS-Recon achieves superior reconstruction quality, particularly at higher acceleration rates. These results highlight the benefit of case-specific adaptive sampling and demonstrate the potential of joint sampling–reconstruction optimization for dynamic MRI. Code and trained models will be made publicly available upon acceptance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-yiasemis26a, title = {End-to-End Co-Optimization of Adaptive $k$-space Sampling and Reconstruction for Dynamic MRI}, author = {Yiasemis, George and Sonke, Jan-Jakob and Teuwen, Jonas}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {1285--1324}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/yiasemis26a/yiasemis26a.pdf}, url = {https://proceedings.mlr.press/v315/yiasemis26a.html}, abstract = {Accelerating dynamic MRI is essential for advancing clinical imaging and improving patient comfort. Most deep learning methods for dynamic MRI reconstruction rely on predetermined or random subsampling patterns that are uniformly applied across all temporal frames. Such strategies ignore temporal correlations and fail to optimize sampling for individual cases. To address this, we propose E2E-ADS-Recon, an end-to-end framework for adaptive dynamic MRI subsampling and reconstruction. The framework integrates an Adaptive Dynamic Sampler (ADS), which generates case-specific sampling patterns for a given acceleration factor, with a dynamic MRI reconstruction network that reconstructs the adaptively sampled data into a dynamic image sequence. The ADS can produce either frame-specific or unified patterns across time frames. We evaluate the method on multi-coil cardiac cine MRI data under both 1D and 2D sampling settings and compare it with standard and optimized non-adaptive baselines. E2E-ADS-Recon achieves superior reconstruction quality, particularly at higher acceleration rates. These results highlight the benefit of case-specific adaptive sampling and demonstrate the potential of joint sampling–reconstruction optimization for dynamic MRI. Code and trained models will be made publicly available upon acceptance.} }
Endnote
%0 Conference Paper %T End-to-End Co-Optimization of Adaptive $k$-space Sampling and Reconstruction for Dynamic MRI %A George Yiasemis %A Jan-Jakob Sonke %A Jonas Teuwen %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-yiasemis26a %I PMLR %P 1285--1324 %U https://proceedings.mlr.press/v315/yiasemis26a.html %V 315 %X Accelerating dynamic MRI is essential for advancing clinical imaging and improving patient comfort. Most deep learning methods for dynamic MRI reconstruction rely on predetermined or random subsampling patterns that are uniformly applied across all temporal frames. Such strategies ignore temporal correlations and fail to optimize sampling for individual cases. To address this, we propose E2E-ADS-Recon, an end-to-end framework for adaptive dynamic MRI subsampling and reconstruction. The framework integrates an Adaptive Dynamic Sampler (ADS), which generates case-specific sampling patterns for a given acceleration factor, with a dynamic MRI reconstruction network that reconstructs the adaptively sampled data into a dynamic image sequence. The ADS can produce either frame-specific or unified patterns across time frames. We evaluate the method on multi-coil cardiac cine MRI data under both 1D and 2D sampling settings and compare it with standard and optimized non-adaptive baselines. E2E-ADS-Recon achieves superior reconstruction quality, particularly at higher acceleration rates. These results highlight the benefit of case-specific adaptive sampling and demonstrate the potential of joint sampling–reconstruction optimization for dynamic MRI. Code and trained models will be made publicly available upon acceptance.
APA
Yiasemis, G., Sonke, J. & Teuwen, J.. (2026). End-to-End Co-Optimization of Adaptive $k$-space Sampling and Reconstruction for Dynamic MRI. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:1285-1324 Available from https://proceedings.mlr.press/v315/yiasemis26a.html.

Related Material