Adaptive Sampling for Linear Sensing Systems via Langevin Dynamics

Adaptive or dynamic signal sampling in sensing systems can adapt subsequent sampling strategies based on acquired signals, thereby potentially improving image quality and speed. This paper proposes a Bayesian method for adaptive sampling based on greedy variance reduction and stochastic gradient Langevin dynamics (SGLD). The image priors involved can be either analytical or neural network-based. Notably, the learned image priors generalize well to out-of-distribution test cases that have different statistics than the training dataset. As a real-world validation, the method is applied to accelerate the acquisition of magnetic resonance imaging (MRI). Compared to non-adaptive sampling, the proposed method effectively improved the image quality by 2-3 dB in PSNR, and improved the restoration of subtle details.

[1]  T. Jaakkola,et al.  Poisson Flow Generative Models , 2022, NeurIPS.

[2]  Christopher M. Sandino,et al.  SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation , 2022, NeurIPS Datasets and Benchmarks.

[3]  Jong-Chul Ye,et al.  Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  G. Herman,et al.  Fast data-driven learning of parallel MRI sampling patterns for large scale problems , 2021, Scientific Reports.

[5]  Abhishek Kumar,et al.  Score-Based Generative Modeling through Stochastic Differential Equations , 2020, ICLR.

[6]  Christian F. Baumgartner,et al.  Sampling Possible Reconstructions of Undersampled Acquisitions in MR Imaging With a Deep Learned Prior , 2020, IEEE Transactions on Medical Imaging.

[7]  Adriana Romero,et al.  Active MR k-space Sampling with Reinforcement Learning , 2020, MICCAI.

[8]  Pieter Abbeel,et al.  Denoising Diffusion Probabilistic Models , 2020, NeurIPS.

[9]  Yang Song,et al.  Generative Modeling by Estimating Gradients of the Data Distribution , 2019, NeurIPS.

[10]  Pascal Vincent,et al.  Reducing Uncertainty in Undersampled MRI Reconstruction With Active Acquisition , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Pascal Vincent,et al.  fastMRI: An Open Dataset and Benchmarks for Accelerated MRI , 2018, ArXiv.

[12]  Daeun Kim,et al.  OEDIPUS: An Experiment Design Framework for Sparsity-Constrained MRI , 2018, IEEE Transactions on Medical Imaging.

[13]  Richard Frayne,et al.  An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement , 2017, NeuroImage.

[14]  Charles A. Bouman,et al.  A model-based framework for fast dynamic image sampling , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Michael Elad,et al.  ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA , 2014, Magnetic resonance in medicine.

[16]  Yee Whye Teh,et al.  Bayesian Learning via Stochastic Gradient Langevin Dynamics , 2011, ICML.

[17]  Aapo Hyvärinen,et al.  Estimation of Non-Normalized Statistical Models by Score Matching , 2005, J. Mach. Learn. Res..

[18]  Gitta Kutyniok.  Compressed Sensing , 2012 .