Heterogeneity-Adaptive Diffusion Schrödinger Bridge for PET-Guided Whole-Body MRI Translation

Sep 21, 2026

Whole-body multimodal PET/MR is increasingly important, but long PET–MR acquisition time limits efficient clinical deployment. Deep learning–based MRI translation can shorten scans, yet existing models often struggle with whole-body settings because anatomical regions show highly heterogeneous feature distributions and lesions introduce additional cross-modality variability. This work proposes Heterogeneity-Adaptive Diffusion Schrödinger Bridge (HA-DSB), which models translation as stochastic transport between source and target distributions, using region context embeddings from a vision-language model and PET-guided dual-stage guidance for lesion-aware reconstruction.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Introduction

Challenges in whole-body PET/MR translation

Proposed Heterogeneity-Adaptive Diffusion Schrödinger Bridge (HA-DSB)

arXiv :2607 .0740 1v 1 [ cs .CV] 8 Jul 2026 Heterogeneity-Adaptive Diffusion Schrödinger Bridge for PET-Guided Whole-Body MRI Translation Chengbo Wang 1†, Jiacheng Yu 1†, Linjie Bian2†, Ming Qi2 , Xiaosheng Liu2 , Tongtong Che3 , Jichang Zhang3 , Shuyu Li3 , and Shaoli Song2 * and Xiuying Wang 1 * 1 The University of Sydney, Sydney, Australia 2 Department of Nuclear Medicine, Fudan University Shanghai Cancer Center, Shanghai, China 3 State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China . Abstract. While whole-body multimodal medical imaging scanners have been increasingly recognized for more effective medical applications, the excessive long acquisition time in PET–MR scanning is a major obstacle in more efficient clinical practice. Deep learning–based MRI translation provides a potential solution to reduce scan duration. However, current models often focus on specific anatomical regions and face challenges for whole-body scans that consists of highly heterogeneous feature distributions mainly due to (1) different anatomical regions across whole-body, and (2) lesions or pathological tissues. This paper tackles the challenges through a novel Heterogeneity-Adaptive Diffusion Schrödinger Bridge (HA-DSB) framework. By explicitly modeling translation as stochastic transport between source and target distributions, HA-DSB incorporates region context embeddings derived from a vision-language model (VLM) to enable region-specific modeling. To enhance fidelity of the pathological tissue, lesion-aware metabolic prior from PET is integrated directly into the bridge dynamics through a dual-stage guidance mechanism. Specifically, a PET-guided noise modulation module adaptively scales spatial diffusion perturbations during the forward process, while PET features are leveraged during the reverse process to selectively amplify lesion-relevant structures via an attention mechanism. Experiments demonstrate the superiority of our method across different body regions in whole-body MRI translation and show improved translation quality in lesion areas under PET guidance. Our code is available at [https://github.com/xyw-medical-research/HADSB](https://github.com/xyw-medical-research/HADSB). Keywords: Medical Image Translation · PET/MR Imaging · Diffusion Schrödinger Bridge · Whole-body MR Translation † contributed equally to this [work.](work. cw643@cantab.ac.uk)[ cw643@cantab.ac.uk](work. cw643@cantab.ac.uk), [mryu888@foxmail.com](mryu888@foxmail.com), [blijer@163.com](blijer@163.com) * corresponding authors. 2 C. Wang et al. 1 Introduction Hybrid positron emission tomography combined with magnetic resonance imaging (PET/MR) is an emerging imaging modality that enables simultaneous acquisition of metabolic and high-resolution anatomical information, producing intrinsically co-registered PET and multi-sequence MR images while reducing radiation exposure compared with PET/CT [1] . Whole-body PET/MR supports comprehensive multi-bed imaging from the head and neck to the mid-thigh and has become increasingly important in clinical applications such as cancer metastasis evaluation [2] . However, whole-body PET/MR scan time typically ranges from 60–90 minutes, largely due to multiple MR sequences, which limits clinical efficiency and increases patient discomfort. Deep learning–based MR translation offers a practical solution by synthesizing time-consuming modalities from fastacquired sequences, and recent diffusion-based approaches have demonstrated promising performance in MR image translation [3–6] . However, most MR translation focus on specific anatomical regions such asthe brain in public datasets [7], and extending these models to whole-body MR translation in integrated PET/MR settings remains challenging. Wholebody scans exhibit strong cross-region heterogeneity, with substantial variations in tissue composition and signal characteristics across anatomical regions [8]

FAQs

Why is whole-body PET–MR scan time a major obstacle in clinical practice?

Whole-body PET–MR typically requires 60–90 minutes due to multiple MR sequences, which reduces clinical efficiency and increases patient discomfort.

What makes whole-body MRI translation more difficult than region-specific translation?

Whole-body scans exhibit strong cross-region heterogeneity, with non-stationary, region-dependent intensity distributions that increase the difficulty of learning a unified mapping.

How does HA-DSB incorporate PET guidance to improve lesion fidelity?

HA-DSB integrates lesion-aware metabolic priors into bridge dynamics via dual-stage guidance: PET-guided noise modulation in the forward process and PET-feature-driven attention in the reverse process to amplify lesion-relevant structures.

Sep 21, 2026

Uploaded by Seraphina