Imperial College London
Alternate

ProfessorDanielRueckert

Faculty of Engineering, Department of Computing

Professor of Visual Information Processing
 
 
 
//

Contact

 

+44 (0)20 7594 8333d.rueckert Website

 
 
//

Location

 

568Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Ziller:2021:10.1038/s41598-021-93030-0,
author = {Ziller, A and Usynin, D and Braren, R and Makowski, M and Rueckert, D and Kaissis, G},
doi = {10.1038/s41598-021-93030-0},
journal = {Scientific Reports},
title = {Medical imaging deep learning with differential privacy},
url = {http://dx.doi.org/10.1038/s41598-021-93030-0},
volume = {11},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The successful training of deep learning models for diagnostic deployment in medical imaging applications requires large volumes of data. Such data cannot be procured without consideration for patient privacy, mandated both by legal regulations and ethical requirements of the medical profession. Differential privacy (DP) enables the provision of information-theoretic privacy guarantees to patients and can be implemented in the setting of deep neural network training through the differentially private stochastic gradient descent (DP-SGD) algorithm. We here present deepee, a free-and-open-source framework for differentially private deep learning for use with the PyTorch deep learning framework. Our framework is based on parallelised execution of neural network operations to obtain and modify the per-sample gradients. The process is efficiently abstracted via a data structure maintaining shared memory references to neural network weights to maintain memory efficiency. We furthermore offer specialised data loading procedures and privacy budget accounting based on the Gaussian Differential Privacy framework, as well as automated modification of the user-supplied neural network architectures to ensure DP-conformity of its layers. We benchmark our framework's computational performance against other open-source DP frameworks and evaluate its application on the paediatric pneumonia dataset, an image classification task and on the Medical Segmentation Decathlon Liver dataset in the task of medical image segmentation. We find that neural network training with rigorous privacy guarantees is possible while maintaining acceptable classification performance and excellent segmentation performance. Our framework compares favourably to related work with respect to memory consumption and computational performance. Our work presents an open-source software framework for differentially private deep learning, which we demonstrate in medical imaging analysis tasks. It serves to further th
AU  - Ziller,A
AU  - Usynin,D
AU  - Braren,R
AU  - Makowski,M
AU  - Rueckert,D
AU  - Kaissis,G
DO  - 10.1038/s41598-021-93030-0
PY  - 2021///
SN  - 2045-2322
TI  - Medical imaging deep learning with differential privacy
T2  - Scientific Reports
UR  - http://dx.doi.org/10.1038/s41598-021-93030-0
UR  - https://www.ncbi.nlm.nih.gov/pubmed/34188157
UR  - http://hdl.handle.net/10044/1/90723
VL  - 11
ER  -
Download