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

arXiv: https://arxiv.org/abs/2501.14171 · HTML: https://mlsanity.com/paper/2501.14171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge](https://mlsanity.com/paper/1811.02629/) (2018)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [Unsupervised Medical Image Translation with Adversarial Diffusion Models](https://mlsanity.com/paper/2207.08208/) (2022)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [Automated brain extraction of multi-sequence MRI using artificial neural networks](https://mlsanity.com/paper/1901.11341/) (2019)
- [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1802.01221/) (2018)
- [Adaptive Diffusion Priors for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2207.05876/) (2022)
- [Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge](https://mlsanity.com/paper/1904.00682/) (2019)
- [Unpaired Image-to-Image Translation via Neural Schr"odinger Bridge](https://mlsanity.com/paper/2305.15086/) (2023)
- [Breaking the Dilemma of Medical Image-to-image Translation](https://mlsanity.com/paper/2110.06465/) (2021)
- [CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis](https://mlsanity.com/paper/2303.14081/) (2023)
- [InstaGAN: Instance-aware Image-to-Image Translation](https://mlsanity.com/paper/1812.10889/) (2018)
- [mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis](https://mlsanity.com/paper/1909.11504/) (2019)
- [I2I-Mamba: Multi-modal medical image synthesis via selective state space modeling](https://mlsanity.com/paper/2405.14022/) (2024)
- [Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation](https://mlsanity.com/paper/2307.16143/) (2023)
- [Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021](https://mlsanity.com/paper/2208.07167/) (2022)
- [Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis](https://mlsanity.com/paper/2212.01108/) (2022)

## Abstract (arXiv)

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.