PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Osuala, R. ; Lang, D.M. ; Riess, A. ; Kaissis, G. ; Szafranowska, Z.* ; Skorupko, G.* ; Diaz, O.* ; Schnabel, J.A. ; Lekadir, K.*

Enhancing the utility of privacy-preserving cancer classification using synthetic data.

In: (Artificial Intelligence and Imaging for Diagnostic and Treatment Challenges in Breast Care). Berlin [u.a.]: Springer, 2025. 54-64 (Lect. Notes Comput. Sc. ; 15451 LNCS)
DOI
Open Access Green möglich sobald Postprint bei der ZB eingereicht worden ist.
Deep learning holds immense promise for aiding radiologists in breast cancer detection. However, achieving optimal model performance is hampered by limitations in availability and sharing of data commonly associated to patient privacy concerns. Such concerns are further exacerbated, as traditional deep learning models can inadvertently leak sensitive training information. This work addresses these challenges exploring and quantifying the utility of privacy-preserving deep learning techniques, concretely, (i) differentially private stochastic gradient descent (DP-SGD) and (ii) fully synthetic training data generated by our proposed malignancy-conditioned generative adversarial network. We assess these methods via downstream malignancy classification of mammography masses using a transformer model. Our experimental results depict that synthetic data augmentation can improve privacy-utility tradeoffs in differentially private model training. Further, model pretraining on synthetic data achieves remarkable performance, which can be further increased with DP-SGD fine-tuning across all privacy guarantees. With this first in-depth exploration of privacy-preserving deep learning in breast imaging, we address current and emerging clinical privacy requirements and pave the way towards the adoption of private high-utility deep diagnostic models. Our reproducible codebase is publicly available at https://github.com/RichardObi/mammo_dp.
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 Breast Imaging ; Differential Privacy ; Generative Models
Sprache englisch
Veröffentlichungsjahr 2025
HGF-Berichtsjahr 2025
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel Artificial Intelligence and Imaging for Diagnostic and Treatment Challenges in Breast Care
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 15451 LNCS, Heft: , Seiten: 54-64 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
Förderungen German Academic Exchange Service (DAAD) under the Kondrad Zuse School of Excellence for Reliable AI (RelAI)
Medical Informatics Initiative as part of the PrivateAIM Project, from the Bavarian Collaborative Research Project PRIPREKI of the Free State of Bavaria Funding Programme "Artificial Intelligence - Data Science"
Bavarian State Ministry for Science and the Arts under the Munich Centre for Machine Learning
German Federal Ministry of Education and Research
Helmholtz Information and Data Science Academy
Ministry of Science and Innovation of Spain
research and innovation programme
DOI 10.1007/978-3-031-77789-9_6
WOS ID 001544124300006
Scopus ID 85219207908
Erfassungsdatum 2025-05-06
[➜Korrektur melden]