A Proof-of-Concept Study of Multitask Learning for Cranial Synthetic CT Generation Across Heterogeneous MRI Field Strengths

Zhuoyao Xin; Yiren Zhang; Christopher Wu; Dong Liu; Chunming Gu; Elena Greco; Erik H. Middlebrooks; Jun Hua

eess.IVApr 30, 2026

A Proof-of-Concept Study of Multitask Learning for Cranial Synthetic CT Generation Across Heterogeneous MRI Field Strengths

Authors: Zhuoyao Xin, Yiren Zhang, Christopher Wu, Dong Liu, Chunming Gu, Elena Greco, Erik H. Middlebrooks, Jun Hua, +1 more

Organizations: F.M. Kirby Research Center for Brain Imaging, Kennedy Krieger Institute, Baltimore, Maryland, 21205, United States. · Neurosection, Division of MR Research, Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, 21287, United States. · Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, 21218, United States. · Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, 44106-4207, United States. · Department of Biomedical Engineering, Columbia University, New York, New York, 10027, United States. · Department of Neuroscience, Columbia University, New York, New York, 10027, United States. · Department of Radiology, Mayo Clinic, Rochester, Minnesota, 55905, United States. · Neuroradiology and Neurosurgery, Mayo Clinic College of Medicine and Science, Jacksonville, Florida, 32224, United States. · Department of Radiology, Johns Hopkins University School of Medicine, 600 N. Wolfe Street, Baltimore, MD 21287, USA

Abstract

Accurate synthesis of computed tomography (CT) images from magnetic resonance imaging (MRI) is clinically valuable for cranial applications such as attenuation correction, radiotherapy planning, and image-guided interventions. However, heterogeneity across MRI field strengths and acquisition protocols limits the generalizability of existing methods. In this study, we formulate cranial CT synthesis as a modular, structurally coupled problem and propose a deep learning framework to improve robustness across heterogeneous MRI conditions. The model is designed to adapt to variations in field strength and imaging protocols while preserving anatomical consistency. Experiments on multi-site datasets demonstrate improved performance and generalization compared with conventional approaches. The proposed method enables reliable CT synthesis across heterogeneous MRI settings, supporting broader clinical translation.

Explore similar work

Task-Adaptive 3D Cross-Field MRI Translation via Field-Conditioned Content-Style Pretraining
Aug 10, 2026Haowen Pang, Yingqi Hao, Pengli ZhuMagnetic Resonance Imaging 3D Latent Diffusion Model
Fast Cross-Strength Multi-Contrast Brain MRI Translation using Latent Bridge Matching
Sep 17, 2026Siddharth Srivastava, Till BretschneiderMagnetic Resonance Imaging Medical Image Generation
Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report
May 13, 2026Viktor Rogowski, Maarten L. Terpstra, Niklas Wahl +30Cone-Beam Computed Tomography Radiotherapy

Aug 10, 2026 · cs.CVJ/K move · Enter open · S save

Task-Adaptive 3D Cross-Field MRI Translation via Field-Conditioned Content-Style Pretraining

Haowen Pang, Yingqi Hao, Pengli Zhu

School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China · School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University, Beijing, China · Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, China

Magnetic field strength is a major source of domain shift in magnetic resonance imaging (MRI), affecting signal-to-noise ratio, tissue contrast, spatial detail, and the visibility of anatomical boundaries. The MRIxFields 2026 challenge investigates this problem through cross-field MRI translation across acquisitions at 0.1T, 1.5T, 3T, 5T, and 7T. Its three tasks, Any-to-7T, 0.1T-to-High, and Any-to-Any synthesis, require the generation of target-field image characteristics while preserving subject-specific anatomy. This problem is particularly challenging because paired acquisitions of the same subject across multiple field strengths are rarely available for training. We propose a 3D unpaired cross-field MRI translation framework based on field-conditioned content-style pretraining. The proposed framework first learns controllable field-to-field translation across all available field strengths by disentangling anatomical content from field-dependent contrast characteristics. The pretrained backbone is then adapted to task-specific target domains. Our model comprises a 3D content encoder, a 3D style encoder, a field-conditioned style generator, an AdaIN-modulated decoder, and a multi-field discriminator. Adversarial learning encourages realistic target-field appearance, while cycle-consistency, identity, content, style, and diversity constraints promote anatomical fidelity and controllable translation. We evaluate the proposed method on MRIxFields data spanning five field strengths and three MRI modalities. Experiments on paired test data demonstrate that the framework can adapt to the three challenge settings while preserving three-dimensional anatomical structure in the synthesized volumes. The implementation code is publicly available at https://github.com/Idea89560041/3D-MRI-Field-Translation.

Magnetic Resonance Imaging 3D Latent Diffusion Model Anatomy Stress Fields Model Pretraining

Open paper Ask about it PDF

Abstract

Explore similar work

Task-Adaptive 3D Cross-Field MRI Translation via Field-Conditioned Content-Style Pretraining

Fast Cross-Strength Multi-Contrast Brain MRI Translation using Latent Bridge Matching

Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report