PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Scholz, D.* ; Erdur, A.C.* ; Holland, R.* ; Ehm, V.* ; Peeken, J.C. ; Wiestler, B.* ; Rueckert, D.*

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

In: (28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025, 23-27 September 2025, Daejeon). Berlin [u.a.]: Springer, 2026. 100-110 (Lect. Notes Comput. Sc. ; 15965 LNCS)
DOI
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 scanners. 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. (The code is publicly available at: https://github.com/daniel-scholz/cacd).
Altmetric
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Konferenzbeitrag
Schlagwörter Contrastive Learning ; Disentanglement ; Domain Generalization ; Scanner Harmonization
Sprache englisch
Veröffentlichungsjahr 2026
Prepublished im Jahr 2025
HGF-Berichtsjahr 2025
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
Konferzenzdatum 23-27 September 2025
Konferenzort Daejeon
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 15965 LNCS, Heft: , Seiten: 100-110 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Institut(e) Institute of Radiation Medicine (IRM)
POF Topic(s) 30203 - Molecular Targets and Therapies
Forschungsfeld(er) Radiation Sciences
PSP-Element(e) G-501300-001
DOI 10.1007/978-3-032-04978-0_10
Scopus ID 105017856389
Erfassungsdatum 2025-10-23
[➜Korrektur melden]