# SPICER: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation and Reconstruction

arXiv: https://arxiv.org/abs/2210.02584 · HTML: https://mlsanity.com/paper/2210.02584/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2022.

## Built on by (most cited first, 10 of 10)

- [Block Coordinate Plug-and-Play Methods for Blind Inverse Problems](https://mlsanity.com/paper/2305.12672/) (2023)
- [Measurement Score-Based Diffusion Model](https://mlsanity.com/paper/2505.11853/) (2025)
- [Robust multi-coil MRI reconstruction via self-supervised denoising](https://mlsanity.com/paper/2411.12919/) (2024)
- [Benchmarking Self-Supervised Learning Methods for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2502.14009/) (2025)
- [Fast MRI for All: Bridging Access Gaps by Training without Raw Data](https://mlsanity.com/paper/2411.13022/) (2024)
- [ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction](https://mlsanity.com/paper/2411.16535/) (2024)
- [Advancing MRI Reconstruction: A Systematic Review of Deep Learning and Compressed Sensing Integration](https://mlsanity.com/paper/2501.14158/) (2025)
- [Measurement Score-Based MRI Reconstruction with Automatic Coil Sensitivity Estimation](https://mlsanity.com/paper/2509.18402/) (2025)
- [Parallel qMRI Reconstruction from 4x Accelerated Acquisitions](https://mlsanity.com/paper/2511.18232/) (2025)
- [Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors](https://mlsanity.com/paper/2606.15110/) (2026)

## Abstract (arXiv)

Deep model-based architectures (DMBAs) integrating physical measurement models and learned image regularizers are widely used in parallel magnetic resonance imaging (PMRI). Traditional DMBAs for PMRI rely on pre-estimated coil sensitivity maps (CSMs) as a component of the measurement model. However, estimation of accurate CSMs is a challenging problem when measurements are highly undersampled. Additionally, traditional training of DMBAs requires high-quality groundtruth images, limiting their use in applications where groundtruth is difficult to obtain. This paper addresses these issues by presenting SPICE as a new method that integrates self-supervised learning and automatic coil sensitivity estimation. Instead of using pre-estimated CSMs, SPICE simultaneously reconstructs accurate MR images and estimates high-quality CSMs. SPICE also enables learning from undersampled noisy measurements without any groundtruth. We validate SPICE on experimentally collected data, showing that it can achieve state-of-the-art performance in highly accelerated data acquisition settings (up to 10x).