PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Daum, D. ; Osuala, R. ; Riess, A. ; Kaissis, G. ; Schnabel, J.A. ; di Folco, M.

On differentially private 3D medical image synthesis with controllable latent diffusion models.

In: (Deep Generative Models). Berlin [u.a.]: Springer, 2025. 139-149 (Lect. Notes Comput. Sc. ; 15224 LNCS)
DOI
Generally, the small size of public medical imaging datasets coupled with stringent privacy concerns, hampers the advancement of data-hungry deep learning models in medical imaging. This study addresses these challenges for 3D cardiac MRI images in the short-axis view. We propose Latent Diffusion Models that generate synthetic images conditioned on medical attributes, while ensuring patient privacy through differentially private model training. To our knowledge, this is the first work to apply and quantify differential privacy in 3D medical image generation. We pre-train our models on public data and finetune them with differential privacy on the UK Biobank dataset. Our experiments reveal that pre-training significantly improves model performance, achieving a Fréchet Inception Distance (FID) of 26.77 at ϵ=10, compared to 92.52 for models without pre-training. Additionally, we explore the trade-off between privacy constraints and image quality, investigating how tighter privacy budgets affect output controllability and may lead to degraded performance. Our results demonstrate that proper consideration during training with differential privacy can substantially improve the quality of synthetic cardiac MRI images, but there are still notable challenges in achieving consistent medical realism. Code: https://github.com/compai-lab/2024-miccai-dgm-daum.
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 Cardiac Mri ; Differential Privacy ; Generative Models ; Synthetic Data
Sprache englisch
Veröffentlichungsjahr 2025
HGF-Berichtsjahr 2025
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel Deep Generative Models
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 15224 LNCS, Heft: , Seiten: 139-149 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)
POF Topic(s) 30205 - Bioengineering and Digital Health
Forschungsfeld(er) Enabling and Novel Technologies
PSP-Element(e) G-507100-001
DOI 10.1007/978-3-031-72744-3_14
Scopus ID 85206989618
Erfassungsdatum 2024-10-30
[➜Korrektur melden]