We present $\zeta$-DP, an extension of differential privacy (DP) to complex-valued functions.
$\psi$ uniquely characterises the GM and its properties by encapsulating its two fundamental quantities: the sensitivity of the query and the magnitude of the noise perturbation.
We introduce Tritium, an automatic differentiation-based sensitivity analysis framework for differentially private (DP) machine learning (ML).
However, while techniques such as individual R\'enyi DP (RDP) allow for granular, per-person privacy accounting, few works have investigated the impact of each input feature on the individual's privacy loss.
In this work, we tackle the problem of Semi-Supervised Anomaly Segmentation (SAS) in Magnetic Resonance Images (MRI) of the brain, which is the task of automatically identifying pathologies in brain images.
1 code implementation • 30 Aug 2021 • Johannes C. Paetzold, Julian McGinnis, Suprosanna Shit, Ivan Ezhov, Paul Büschl, Chinmay Prabhakar, Mihail I. Todorov, Anjany Sekuboyina, Georgios Kaissis, Ali Ertürk, Stephan Günnemann, Bjoern H. Menze
Moreover, we benchmark numerous state-of-the-art graph learning algorithms on the biologically relevant tasks of vessel prediction and vessel classification using the introduced vessel graph dataset.
The application of differential privacy to the training of deep neural networks holds the promise of allowing large-scale (decentralized) use of sensitive data while providing rigorous privacy guarantees to the individual.
Reconciling large-scale ML with the closed-form reasoning required for the principled analysis of individual privacy loss requires the introduction of new tools for automatic sensitivity analysis and for tracking an individual's data and their features through the flow of computation.
We show that differentially private stochastic gradient descent (DP-SGD) can yield poorly calibrated, overconfident deep learning models.
The application of PTs to FL in medical imaging and the trade-offs between privacy guarantees and model utility, the ramifications on training performance and the susceptibility of the final models to attacks have not yet been conclusively investigated.
Federated learning (FL) enables multiple clients to jointly train a global model under the coordination of a central server.
Deep Neural Networks (DNNs) are widely used for decision making in a myriad of critical applications, ranging from medical to societal and even judicial.
no code implementations • 10 Dec 2020 • Alexander Ziller, Jonathan Passerat-Palmbach, Théo Ryffel, Dmitrii Usynin, Andrew Trask, Ionésio Da Lima Costa Junior, Jason Mancuso, Marcus Makowski, Daniel Rueckert, Rickmer Braren, Georgios Kaissis
The utilisation of artificial intelligence in medicine and healthcare has led to successful clinical applications in several domains.
For artificial intelligence-based image analysis methods to reach clinical applicability, the development of high-performance algorithms is crucial.
6 code implementations • 13 Jan 2019 • Patrick Bilic, Patrick Ferdinand Christ, Grzegorz Chlebus, Hao Chen, Qi Dou, Chi-Wing Fu, Xiao Han, Pheng-Ann Heng, Jürgen Hesser, Samuel Kadoury, Tomasz Konopczynski, Miao Le, Chunming Li, Xiaomeng Li, Jana Lipkovà, John Lowengrub, Hans Meine, Jan Hendrik Moltz, Chris Pal, Marie Piraud, Xiaojuan Qi, Jin Qi, Markus Rempfler, Karsten Roth, Andrea Schenk, Anjany Sekuboyina, Eugene Vorontsov, Ping Zhou, Christian Hülsemeyer, Marcel Beetz, Florian Ettlinger, Felix Gruen, Georgios Kaissis, Fabian Lohöfer, Rickmer Braren, Julian Holch, Felix Hofmann, Wieland Sommer, Volker Heinemann, Colin Jacobs, Gabriel Efrain Humpire Mamani, Bram van Ginneken, Gabriel Chartrand, An Tang, Michal Drozdzal, Avi Ben-Cohen, Eyal Klang, Marianne M. Amitai, Eli Konen, Hayit Greenspan, Johan Moreau, Alexandre Hostettler, Luc Soler, Refael Vivanti, Adi Szeskin, Naama Lev-Cohain, Jacob Sosna, Leo Joskowicz, Bjoern H. Menze
The best liver segmentation algorithm achieved a Dice score of 0. 96(MICCAI) whereas for tumor segmentation the best algorithm evaluated at 0. 67(ISBI) and 0. 70(MICCAI).
1 code implementation • 20 Feb 2017 • Patrick Ferdinand Christ, Florian Ettlinger, Georgios Kaissis, Sebastian Schlecht, Freba Ahmaddy, Felix Grün, Alexander Valentinitsch, Seyed-Ahmad Ahmadi, Rickmer Braren, Bjoern Menze
A 3D neural network (SurvivalNet) then predicts the HCC lesions' malignancy from the HCC tumor segmentation.
4 code implementations • 20 Feb 2017 • Patrick Ferdinand Christ, Florian Ettlinger, Felix Grün, Mohamed Ezzeldin A. Elshaera, Jana Lipkova, Sebastian Schlecht, Freba Ahmaddy, Sunil Tatavarty, Marc Bickel, Patrick Bilic, Markus Rempfler, Felix Hofmann, Melvin D Anastasi, Seyed-Ahmad Ahmadi, Georgios Kaissis, Julian Holch, Wieland Sommer, Rickmer Braren, Volker Heinemann, Bjoern Menze
In the first step, we train a FCN to segment the liver as ROI input for a second FCN.