Towards Trustworthy Selective Generation: Reliability-Guided Diffusion for Ultra-Low-Field to High-Field MRI Synthesis

2026-03-11

AI Summary

This work addresses the challenge of anatomical inconsistencies and structural blurring in synthetic high-field MRI images generated from low-field inputs using existing diffusion models, which undermine clinical reliability. To mitigate this issue, the authors propose ReDiff, a reliability-aware diffusion framework that integrates reliability-guided sampling with an uncertainty-driven multi-candidate selection mechanism. This approach dynamically balances structural fidelity and anatomical plausibility during image generation. Comprehensive experiments on multi-center MRI datasets demonstrate that ReDiff substantially reduces artifacts and outperforms state-of-the-art methods, yielding synthetic images with significantly enhanced clinical credibility.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Low-field to high-field MRI synthesis has emerged as a cost-effective strategy to enhance image quality under hardware and acquisition constraints, particularly in scenarios where access to high-field scanners is limited or impractical. Despite recent progress in diffusion models, diffusion-based approaches often struggle to balance fine-detail recovery and structural fidelity. In particular, the uncontrolled generation of high-resolution details in structurally ambiguous regions may introduce anatomically inconsistent patterns, such as spurious edges or artificial texture variations. These artifacts can bias downstream quantitative analysis. For example, they may cause inaccurate tissue boundary delineation or erroneous volumetric estimation, ultimately reducing clinical trust in synthesized images. These limitations highlight the need for generative models that are not only visually accurate but also spatially reliable and anatomically consistent. To address this issue, we propose a reliability-aware diffusion framework (ReDiff) that improves synthesis robustness at both the sampling and post-generation stages. Specifically, we introduce a reliability-guided sampling strategy to suppress unreliable responses during the denoising process. We further develop an uncertainty-aware multi-candidate selection scheme to enhance the reliability of the final prediction. Experiments on multi-center MRI datasets demonstrate improved structural fidelity and reduced artifacts compared with state-of-the-art methods.

Problem

• MRI synthesis
• structural fidelity
• anatomical consistency
• generative artifacts
• diffusion models

Innovation

• reliability-guided diffusion
• ultra-low-field MRI synthesis
• structural fidelity
• uncertainty-aware selection
• anatomical consistency