Fully Guided Neural Schr\"odinger bridge for Brain MR image synthesis

TL;DR

This paper introduces FGSB, a novel neural Schr"odinger bridge framework for high-fidelity brain MRI modality synthesis, especially effective with limited paired data and lesion preservation.

Contribution

The proposed FGSB method enables accurate MRI modality synthesis with minimal paired data and preserves critical lesions using lesion-specific priors.

Findings

FGSB achieves reliable synthesis across various datasets and resolutions.

Incorporating lesion priors improves lesion preservation in generated images.

The two-stage process refines images and models transformation pathways for high fidelity.

Abstract

Multi-modal brain MRI provides essential complementary information for clinical diagnosis. However, acquiring all modalities in practice is often constrained by time and cost. To address this, various methods have been proposed to generate missing modalities from available ones. Existing approaches can be broadly categorized into two types: paired and unpaired methods. While paired methods achieve high synthesis accuracy, obtaining large-scale paired datasets is typically impractical. In contrast, unpaired methods, though more scalable, often fail to preserve critical anatomical features, such as lesions. In this paper, we propose Fully Guided Schr\"odinger Bridge (FGSB), a novel framework designed to overcome these limitations by enabling high-fidelity generation with extremely limited paired data. When lesion-specific information, such as expert annotations or segmentation masks, is available, FGSB preserves clinically relevant lesions during missing modality synthesis. Our model comprises two stages: (1) a generation stage that iteratively refines synthetic images using paired source images and Gaussian noise, and (2) a training stage that learns optimal transformation pathways by modeling intermediate states to ensure consistent, high-fidelity synthesis. Experimental results across multiple datasets demonstrate that FGSB achieves reliable synthesis performance across diverse imaging resolutions and data acquisition environments. In addition, incorporating lesion-specific priors further enhances the preservation of clinically relevant features.