Contrastive Anatomy-Contrast Disentanglement: A Domain-General MRI Harmonization Method

MCML Authors

Daniel Scholz

→ Group Benedikt Wiestler
 AI for Image-Guided Diagnosis and Therapy

Viktoria Ehm

→ Group Daniel Cremers
 Computer Vision & Artificial Intelligence

Benedikt Wiestler

Prof. Dr.

Principal Investigator

AI for Image-Guided Diagnosis and Therapy

Daniel Rückert

Prof. Dr.

Director

Artificial Intelligence in Healthcare and Medicine

Abstract

Magnetic resonance imaging (MRI) is an invaluable tool for clinical and research applications. Yet, variations in scanners and acquisition parameters cause inconsistencies in image contrast, hindering data comparability and reproducibility across datasets and clinical studies. Existing scanner harmonization methods, designed to address this challenge, face limitations, such as requiring traveling subjects or struggling to generalize to unseen domains. We propose a novel approach using a conditioned diffusion autoencoder with a contrastive loss and domain-agnostic contrast augmentation to harmonize MR images across scanners while preserving subject-specific anatomy. Our method enables brain MRI synthesis from a single reference image. It outperforms baseline techniques, achieving a +7% PSNR improvement on a traveling subjects dataset and +18% improvement on age regression in unseen. Our model provides robust, effective harmonization of brain MRIs to target scanners without requiring fine-tuning. This advancement promises to enhance comparability, reproducibility, and generalizability in multi-site and longitudinal clinical studies, ultimately contributing to improved healthcare outcomes.

inproceedings

---

MICCAI 2025

28th International Conference on Medical Image Computing and Computer Assisted Intervention. Daejeon, Republic of Korea, Sep 23-27, 2025.

---

Authors

D. Scholz • A. C. Erdur • R. Holland • V. Ehm • J. C. Peeken • B. Wiestler • D. Rückert

---

Links

DOI

---

Research Areas

 B1 | Computer Vision

 C1 | Medicine