Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Open World MRI Reconstruction with Bias-Calibrated Adaptation

Jiyao Liu, Shangqi Gao, Lihao Liu, Junzhi Ning, Jinjie Wei, Junjun He, Xiahai Zhuang, Ningsheng Xu

Abstract

Real-world MRI reconstruction systems face the open-world challenge: test data from unseen imaging centers, anatomical structures, or acquisition protocols can differ drastically from training data, causing severe performance degradation. Existing methods struggle with this challenge. To address this, we propose BiasRecon, a bias-calibrated adaptation framework grounded in the minimal intervention principle: preserve what transfers, calibrate what does not. Concretely, BiasRecon formulates open-world adaptation as an alternating optimization framework that jointly optimizes three components: (1) frequency-guided prior calibration that introduces layer-wise calibration variables to selectively modulate frequency-specific features of the pre-trained score network via self-supervised k-space signals, (2) score-based denoising that leverages the calibrated generative prior for high-fidelity image reconstruction, and (3) adaptive regularization that employs Stein's Unbiased Risk Estimator to dynamically balance the prior-measurement trade-off, matching test-time noise characteristics without requiring ground truth. By intervening minimally and precisely through this alternating scheme, BiasRecon achieves robust adaptation with fewer than 100 tunable parameters. Extensive experiments across four datasets demonstrate state-of-the-art performance on open-world reconstruction tasks.

Open World MRI Reconstruction with Bias-Calibrated Adaptation

Abstract

Real-world MRI reconstruction systems face the open-world challenge: test data from unseen imaging centers, anatomical structures, or acquisition protocols can differ drastically from training data, causing severe performance degradation. Existing methods struggle with this challenge. To address this, we propose BiasRecon, a bias-calibrated adaptation framework grounded in the minimal intervention principle: preserve what transfers, calibrate what does not. Concretely, BiasRecon formulates open-world adaptation as an alternating optimization framework that jointly optimizes three components: (1) frequency-guided prior calibration that introduces layer-wise calibration variables to selectively modulate frequency-specific features of the pre-trained score network via self-supervised k-space signals, (2) score-based denoising that leverages the calibrated generative prior for high-fidelity image reconstruction, and (3) adaptive regularization that employs Stein's Unbiased Risk Estimator to dynamically balance the prior-measurement trade-off, matching test-time noise characteristics without requiring ground truth. By intervening minimally and precisely through this alternating scheme, BiasRecon achieves robust adaptation with fewer than 100 tunable parameters. Extensive experiments across four datasets demonstrate state-of-the-art performance on open-world reconstruction tasks.
Paper Structure (13 sections, 7 equations, 5 figures, 3 tables)

This paper contains 13 sections, 7 equations, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Bias-Calibrated Adaptation Framework
  4. Frequency-guided Prior Calibration
  5. Regularization Parameter Adaptation
  6. Experiments
  7. Experimental Setup
  8. Open-World Evaluation
  9. Robustness against Distribution Shifts.
  10. Robustness against undersampling.
  11. Parameter Analysis
  12. Ablation Study
  13. Conclusion

Figures (5)

  • Figure 1: Transferability analysis. (a) Open-world distribution shifts from anatomy, center, and modality changes. Models trained on FastMRI knee (inside dashed box) are tested on three OOD scenarios. (b) t-SNE visualization of features from bottom (deeper) and top (shallow) layers across different domains. (c) Frequency decomposition analysis of low-frequency and high-frequency components across different domains.
  • Figure 2: Overview of BiasRecon framework. The top panel illustrates the alternating optimization process of BiasRecon. The framework consists of three key components: a) Frequency-guided Prior Calibration, which adaptively adjusts feature distributions through parameter-efficient modulation; b) Score-based reverse sampling process as the foundation; and c) Regularization Parameter Adaptation, which dynamically balances measurement consistency and prior constraints.
  • Figure 3: Illustration of frequency-guided prior calibration.
  • Figure 4: Dynamic evolution of calibration variables and regularization parameter during the reconstruction process.
  • Figure 5: Qualitative comparison of MRI reconstruction results under 8$\times$ Gaussian 1D undersampling.