Miniatura

Fitxers

DeepBreath_MICCAI_Workshop_Paper_2024.pdf (2.2 MB)

Tipus de document

Objecte de conferència

Versió

Versió acceptada

Data de publicació

2025-02-11
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/220572

Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data

Títol de la revista

Autors

ISSN de la revista

Títol del volum

Resum

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.

Descripció

Matèries

Càncer de mama, Aprenentatge automàtic, Imatges per ressonància magnètica

Matèries (anglès)

Breast cancer, Machine learning, Magnetic resonance imaging

Citació

Col·leccions

Comunicacions a congressos (Matemàtiques i Informàtica)

Citació

OSUALA, Richard, LANG, Daniel m., RIESS, Anneliese, KAISSIS, Georgios, SZAFRANOWSKA, Zuzanna, SKORUPKO, Grzegorz, DÍAZ, Oliver, SCHNABEL, Julia a., LEKADIR, Karim. Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data. _Comunicació al congrés: Artificial Intelligence and Imaging for Diagnostic and Treatment Challenges in Breast Care: First Deep Breast Workshop_. Deep-Breath 2024. Vol.  Held in Conjunction with MICCAI 2024, núm. Marrakesh, pàgs. Morocco. [consulta: 25 de novembre de 2025]. [Disponible a: https://hdl.handle.net/2445/220572]

Exportar metadades

JSON - METS

Compartir registre