OpenULF: A Modular Toolkit Enables Data-Driven Ultra-Low-Field MRI with both Classical and Quantum Sensors
Abstract
Ultra-low-field (ULF) Magnetic Resonance Imaging (MRI) offers a portable, low-cost alternative to conventional scanners by operating at field strengths below 10 mT. At these fields, two sensor technologies compete: quantum SQUID (Superconducting Quantum Interference Device) sensors, which provide high sensitivity but require cryogenic cooling, and classical induction coils, which are inexpensive and room-temperature but produce weaker signals. With conventional physics-based imaging, both suffer from low signal-to-noise ratios (SNR). Data-driven reconstruction has overcome similar limits in related inverse problems, but its use for ULF-MRI has been hindered by a lack of open datasets, benchmarks, and flexible simulators. To close this gap, we present OpenULF, a modular, open-source simulation toolkit that generates paired training data and supports end-to-end machine-learning (ML) reconstruction. OpenULF integrates a Bloch-equation-validated physics simulator, calibrated SQUID and coil receiver models, reconstruction ML networks, and an automated design-space exploration engine. Architecturally, a receiver abstract base class, a typed HDF5 contract that decouples physics from learning, and a resumable sweep engine make sensors, models, and datasets independently substitutable. Using OpenULF, we train 774 models across four anatomical datasets and conduct three design-space explorations. The effectiveness of ML reconstruction depends strongly on the dataset and the sensor. We identify a SQUID-to-coil crossover near 450 μT and demonstrate that sensor hardware and ML model capacity can be traded off during system design. Sensor and reconstruction choices must therefore be co-designed: the best sensor is set by the dataset and field strength, not by SNR.
Related
- Pauli propagation enables fast classical simulation of strongly correlated quantum systems
- LaQX: A JAX Toolkit for Neural Quantum State Simulations of Lattice Quantum Many-Body Models
- clifford_qc: A Python Toolkit for Quantum Simulation
- Model predictive quantum control: a modular approach for efficient and robust quantum optimal control
- Simulation of quantum entangled states by classical probabilistic models
BibTeX
@misc{wu2026openulf,
title = {{OpenULF: A Modular Toolkit Enables Data-Driven Ultra-Low-Field MRI with both Classical and Quantum Sensors}},
author = {Hanhan Wu and Yuchen Yuan and Weiwen Jiang},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01511},
eprint = {2611.01511},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01511},
}
RIS
TY - UNPB
TI - OpenULF: A Modular Toolkit Enables Data-Driven Ultra-Low-Field MRI with both Classical and Quantum Sensors
AU - Hanhan Wu
AU - Yuchen Yuan
AU - Weiwen Jiang
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01511
UR - https://arxiv.org/abs/2611.01511
AB - Ultra-low-field (ULF) Magnetic Resonance Imaging (MRI) offers a portable, low-cost alternative to conventional scanners by operating at field strengths below 10 mT. At these fields, two sensor technologies compete: quantum SQUID (Superconducting Quantum Interference Device) sensors, which provide high sensitivity but require cryogenic cooling, and classical induction coils, which are inexpensive and room-temperature but produce weaker signals. With conventional physics-based imaging, both suffer from low signal-to-noise ratios (SNR). Data-driven reconstruction has overcome similar limits in related inverse problems, but its use for ULF-MRI has been hindered by a lack of open datasets, benchmarks, and flexible simulators. To close this gap, we present OpenULF, a modular, open-source simulation toolkit that generates paired training data and supports end-to-end machine-learning (ML) reconstruction. OpenULF integrates a Bloch-equation-validated physics simulator, calibrated SQUID and coil receiver models, reconstruction ML networks, and an automated design-space exploration engine. Architecturally, a receiver abstract base class, a typed HDF5 contract that decouples physics from learning, and a resumable sweep engine make sensors, models, and datasets independently substitutable. Using OpenULF, we train 774 models across four anatomical datasets and conduct three design-space explorations. The effectiveness of ML reconstruction depends strongly on the dataset and the sensor. We identify a SQUID-to-coil crossover near 450 μT and demonstrate that sensor hardware and ML model capacity can be traded off during system design. Sensor and reconstruction choices must therefore be co-designed: the best sensor is set by the dataset and field strength, not by SNR.
ER -