# Self-Supervised Deep Active Accelerated MRI

arXiv: https://arxiv.org/abs/1901.04547 · HTML: https://mlsanity.com/paper/1901.04547/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2019.

## Built on by (most cited first, 24 of 24)

- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Active 3D Shape Reconstruction from Vision and Touch](https://mlsanity.com/paper/2107.09584/) (2021)
- [On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction](https://mlsanity.com/paper/2203.16392/) (2022)
- [End-to-End Sequential Sampling and Reconstruction for MRI](https://mlsanity.com/paper/2105.06460/) (2021)
- [A review and experimental evaluation of deep learning methods for MRI reconstruction](https://mlsanity.com/paper/2109.08618/) (2021)
- [Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling](https://mlsanity.com/paper/2407.08256/) (2024)
- [Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction](https://mlsanity.com/paper/2406.04318/) (2024)
- [One Network to Solve Them All: A Sequential Multi-Task Joint Learning Network Framework for MR Imaging Pipeline](https://mlsanity.com/paper/2105.06653/) (2021)
- [PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI](https://mlsanity.com/paper/2204.11189/) (2022)
- [Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning](https://mlsanity.com/paper/2201.09522/) (2022)
- [Matrix Completion-Informed Deep Unfolded Equilibrium Models for Self-Supervised k-Space Interpolation in MRI](https://mlsanity.com/paper/2309.13571/) (2023)
- [Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomography](https://mlsanity.com/paper/2504.03491/) (2025)
- [JoJoNet: Joint-contrast and Joint-sampling-and-reconstruction Network for Multi-contrast MRI](https://mlsanity.com/paper/2210.12548/) (2022)
- [Active CT Reconstruction with a Learned Sampling Policy](https://mlsanity.com/paper/2211.01670/) (2022)
- [On the Feasibility of Machine Learning Augmented Magnetic Resonance for Point-of-Care Identification of Disease](https://mlsanity.com/paper/2301.11962/) (2023)
- [Active Phase-Encode Selection for Slice-Specific Fast MR Scanning Using a Transformer-Based Deep Reinforcement Learning Framework](https://mlsanity.com/paper/2203.05756/) (2022)
- [Learning to sample in Cartesian MRI](https://mlsanity.com/paper/2312.04327/) (2023)
- [Optimal OnTheFly Feedback Control of Event Sensors](https://mlsanity.com/paper/2408.12976/) (2024)
- [A Note on Machine Learning Approach for Computational Imaging](https://mlsanity.com/paper/2202.11883/) (2022)
- [L2SR: Learning to Sample and Reconstruct for Accelerated MRI via Reinforcement Learning](https://mlsanity.com/paper/2212.02190/) (2022)
- [Reinforcement Learning for Sampling on Temporal Medical Imaging Sequences](https://mlsanity.com/paper/2308.14946/) (2023)
- [Reinforcement Learning of Adaptive Acquisition Policies for Inverse Problems](https://mlsanity.com/paper/2407.07794/) (2024)
- [LSST: Learned Single-Shot Trajectory and Reconstruction Network for MR Imaging](https://mlsanity.com/paper/2409.07457/) (2024)
- [Prior-aware and Context-guided Group Sampling for Active Probabilistic Subsampling](https://mlsanity.com/paper/2607.07083/) (2026)

## Abstract (arXiv)

We propose to simultaneously learn to sample and reconstruct magnetic resonance images (MRI) to maximize the reconstruction quality given a limited sample budget, in a self-supervised setup. Unlike existing deep methods that focus only on reconstructing given data, thus being passive, we go beyond the current state of the art by considering both the data acquisition and the reconstruction process within a single deep-learning framework. As our network learns to acquire data, the network is active in nature. In order to do so, we simultaneously train two neural networks, one dedicated to reconstruction and the other to progressive sampling, each with an automatically generated supervision signal that links them together. The two supervision signals are created through Monte Carlo tree search (MCTS). MCTS returns a better sampling pattern than what the current sampling network can give and, thus, a better final reconstruction. The sampling network is trained to mimic the MCTS results using the previous sampling network, thus being enhanced. The reconstruction network is trained to give the highest reconstruction quality, given the MCTS sampling pattern. Through this framework, we are able to train the two networks without providing any direct supervision on sampling.