Open World MRI Reconstruction with Bias-Calibrated Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jiyao, Gao, Shangqi, Liu, Lihao, Ning, Junzhi, Wei, Jinjie, He, Junjun, Zhuang, Xiahai, Xu, Ningsheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914392553029632
author Liu, Jiyao
Gao, Shangqi
Liu, Lihao
Ning, Junzhi
Wei, Jinjie
He, Junjun
Zhuang, Xiahai
Xu, Ningsheng
author_facet Liu, Jiyao
Gao, Shangqi
Liu, Lihao
Ning, Junzhi
Wei, Jinjie
He, Junjun
Zhuang, Xiahai
Xu, Ningsheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13466
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Open World MRI Reconstruction with Bias-Calibrated Adaptation
Liu, Jiyao
Gao, Shangqi
Liu, Lihao
Ning, Junzhi
Wei, Jinjie
He, Junjun
Zhuang, Xiahai
Xu, Ningsheng
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Open World MRI Reconstruction with Bias-Calibrated Adaptation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.13466