arXiv subjects

Jonathan Passerat-Palmbach

Publications and source records attributed to Jonathan Passerat-Palmbach.

34 records · Page 2Linked to original sources

arXiv2020

A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classification

This work provides a comprehensive review of existing frameworks based on secure computing techniques in the context of private image classification. The in-depth analysis of these approaches is followed by careful examination of their performance costs, in particular runtime and communication overhead. To further illustrate the practical considerations when using different privacy-preserving technologies, experiments were conducted using four state-of-the-art libraries implementing secure computing at the heart of the data science stack: PySyft and CrypTen supporting private inference via Secure Multi-Party Computation, TF-Trusted utilising Trusted Execution Environments and HE- Transformer relying on Homomorphic encryption. Our work aims to evaluate the suitability of these frameworks from a usability, runtime requirements and accuracy point of view. In order to better understand the gap between state-of-the-art protocols and what is currently available in practice for a data scientist, we designed three neural network architecture to obtain secure predictions via each of the four aforementioned frameworks. Two networks were evaluated on the MNIST dataset and one on the Malaria Cell image dataset. We observed satisfying performances for TF-Trusted and CrypTen and noted that all frameworks perfectly preserved the accuracy of the corresponding plaintext model.

cs.CR↗

arXiv2020

Robust Aggregation for Adaptive Privacy Preserving Federated Learning in Healthcare

Federated learning (FL) has enabled training models collaboratively from multiple data owning parties without sharing their data. Given the privacy regulations of patient's healthcare data, learning-based systems in healthcare can greatly benefit from privacy-preserving FL approaches. However, typical model aggregation methods in FL are sensitive to local model updates, which may lead to failure in learning a robust and accurate global model. In this work, we implement and evaluate different robust aggregation methods in FL applied to healthcare data. Furthermore, we show that such methods can detect and discard faulty or malicious local clients during training. We run two sets of experiments using two real-world healthcare datasets for training medical diagnosis classification tasks. Each dataset is used to simulate the performance of three different robust FL aggregation strategies when facing different poisoning attacks. The results show that privacy preserving methods can be successfully applied alongside Byzantine-robust aggregation techniques. We observed in particular how using differential privacy (DP) did not significantly impact the final learning convergence of the different aggregation strategies.

cs.CR↗

arXiv2019

A blockchain-orchestrated Federated Learning architecture for healthcare consortia

We propose a novel architecture for federated learning within healthcare consortia. At the heart of the solution is a unique integration of privacy preserving technologies, built upon native enterprise blockchain components available in the Ethereum ecosystem. We show how the specific characteristics and challenges of healthcare consortia informed our design choices, notably the conception of a new Secure Aggregation protocol assembled with a protected hardware component and an encryption toolkit native to Ethereum. Our architecture also brings in a privacy preserving audit trail that logs events in the network without revealing identities.

cs.CY↗

arXiv2018

A generic framework for privacy preserving deep learning

We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valuable representation based on chains of commands and tensors. This abstraction allows one to implement complex privacy preserving constructs such as Federated Learning, Secure Multiparty Computation, and Differential Privacy while still exposing a familiar deep learning API to the end-user. We report early results on the Boston Housing and Pima Indian Diabetes datasets. While the privacy features apart from Differential Privacy do not impact the prediction accuracy, the current implementation of the framework introduces a significant overhead in performance, which will be addressed at a later stage of the development. We believe this work is an important milestone introducing the first reliable, general framework for privacy preserving deep learning.

cs.LG↗

arXiv2018

Learning-Based Quality Control for Cardiac MR Images

The effectiveness of a cardiovascular magnetic resonance (CMR) scan depends on the ability of the operator to correctly tune the acquisition parameters to the subject being scanned and on the potential occurrence of imaging artefacts such as cardiac and respiratory motion. In the clinical practice, a quality control step is performed by visual assessment of the acquired images: however, this procedure is strongly operator-dependent, cumbersome and sometimes incompatible with the time constraints in clinical settings and large-scale studies. We propose a fast, fully-automated, learning-based quality control pipeline for CMR images, specifically for short-axis image stacks. Our pipeline performs three important quality checks: 1) heart coverage estimation, 2) inter-slice motion detection, 3) image contrast estimation in the cardiac region. The pipeline uses a hybrid decision forest method - integrating both regression and structured classification models - to extract landmarks as well as probabilistic segmentation maps from both long- and short-axis images as a basis to perform the quality checks. The technique was tested on up to 3000 cases from the UK Biobank as well as on 100 cases from the UK Digital Heart Project, and validated against manual annotations and visual inspections performed by expert interpreters. The results show the capability of the proposed pipeline to correctly detect incomplete or corrupted scans (e.g. on UK Biobank, sensitivity and specificity respectively 88% and 99% for heart coverage estimation, 85% and 95% for motion detection), allowing their exclusion from the analysed dataset or the triggering of a new acquisition.

cs.CV↗

arXiv2018

Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents

We propose a fully automatic method to find standardized view planes in 3D image acquisitions. Standard view images are important in clinical practice as they provide a means to perform biometric measurements from similar anatomical regions. These views are often constrained to the native orientation of a 3D image acquisition. Navigating through target anatomy to find the required view plane is tedious and operator-dependent. For this task, we employ a multi-scale reinforcement learning (RL) agent framework and extensively evaluate several Deep Q-Network (DQN) based strategies. RL enables a natural learning paradigm by interaction with the environment, which can be used to mimic experienced operators. We evaluate our results using the distance between the anatomical landmarks and detected planes, and the angles between their normal vector and target. The proposed algorithm is assessed on the mid-sagittal and anterior-posterior commissure planes of brain MRI, and the 4-chamber long-axis plane commonly used in cardiac MRI, achieving accuracy of 1.53mm, 1.98mm and 4.84mm, respectively.

cs.CV↗

arXiv2017

Employing Weak Annotations for Medical Image Analysis Problems

To efficiently establish training databases for machine learning methods, collaborative and crowdsourcing platforms have been investigated to collectively tackle the annotation effort. However, when this concept is ported to the medical imaging domain, reading expertise will have a direct impact on the annotation accuracy. In this study, we examine the impact of expertise and the amount of available annotations on the accuracy outcome of a liver segmentation problem in an abdominal computed tomography (CT) image database. In controlled experiments, we study this impact for different types of weak annotations. To address the decrease in accuracy associated with lower expertise, we propose a method for outlier correction making use of a weakly labelled atlas. Using this approach, we demonstrate that weak annotations subject to high error rates can achieve a similarly high accuracy as state-of-the-art multi-atlas segmentation approaches relying on a large amount of expert manual segmentations. Annotations of this nature can realistically be obtained from a non-expert crowd and can potentially enable crowdsourcing of weak annotation tasks for medical image analysis.

cs.CV↗

arXiv2016

Proceedings of the Workshop on Brain Analysis using COnnectivity Networks - BACON 2016

Understanding brain connectivity in a network-theoretic context has shown much promise in recent years. This type of analysis identifies brain organisational principles, bringing a new perspective to neuroscience. At the same time, large public databases of connectomic data are now available. However, connectome analysis is still an emerging field and there is a crucial need for robust computational methods to fully unravelits potential. This workshop provides a platform to discuss the development of new analytic techniques; methods for evaluating and validating commonly used approaches; as well as the effects of variations in pre-processing steps.

cs.NE↗

arXiv2016

Comparison of Brain Networks with Unknown Correspondences

Graph theory has drawn a lot of attention in the field of Neuroscience during the last decade, mainly due to the abundance of tools that it provides to explore the interactions of elements in a complex network like the brain. The local and global organization of a brain network can shed light on mechanisms of complex cognitive functions, while disruptions within the network can be linked to neurodevelopmental disorders. In this effort, the construction of a representative brain network for each individual is critical for further analysis. Additionally, graph comparison is an essential step for inference and classification analyses on brain graphs. In this work we explore a method based on graph edit distance for evaluating graph similarity, when correspondences between network elements are unknown due to different underlying subdivisions of the brain. We test this method on 30 unrelated subjects as well as 40 twin pairs and show that this method can accurately reflect the higher similarity between two related networks compared to unrelated ones, while identifying node correspondences.

q-bio.NC↗

arXiv2016

DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks

In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations. It extends the approach of the well-known GrabCut method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naive approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy.

cs.CV↗

arXiv2016

Learning under Distributed Weak Supervision

The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods. While typically established by a clinical expert rater, the increase in acquired imaging data renders traditional pixel-wise segmentations less feasible. In this paper, we examine the use of a crowdsourcing platform for the distribution of super-pixel weak annotation tasks and collect such annotations from a crowd of non-expert raters. The crowd annotations are subsequently used for training a fully convolutional neural network to address the problem of fetal brain segmentation in T2-weighted MR images. Using this approach we report encouraging results compared to highly targeted, fully supervised methods and potentially address a frequent problem impeding image analysis research.

cs.CV↗

arXiv2016

Multi-Atlas Segmentation using Partially Annotated Data: Methods and Annotation Strategies

Multi-atlas segmentation is a widely used tool in medical image analysis, providing robust and accurate results by learning from annotated atlas datasets. However, the availability of fully annotated atlas images for training is limited due to the time required for the labelling task. Segmentation methods requiring only a proportion of each atlas image to be labelled could therefore reduce the workload on expert raters tasked with annotating atlas images. To address this issue, we first re-examine the labelling problem common in many existing approaches and formulate its solution in terms of a Markov Random Field energy minimisation problem on a graph connecting atlases and the target image. This provides a unifying framework for multi-atlas segmentation. We then show how modifications in the graph configuration of the proposed framework enable the use of partially annotated atlas images and investigate different partial annotation strategies. The proposed method was evaluated on two Magnetic Resonance Imaging (MRI) datasets for hippocampal and cardiac segmentation. Experiments were performed aimed at (1) recreating existing segmentation techniques with the proposed framework and (2) demonstrating the potential of employing sparsely annotated atlas data for multi-atlas segmentation.

cs.CV↗

arXiv2015

Model Exploration Using OpenMOLE - a workflow engine for large scale distributed design of experiments and parameter tuning

OpenMOLE is a scientific workflow engine with a strong emphasis on workload distribution. Workflows are designed using a high level Domain Specific Language (DSL) built on top of Scala. It exposes natural parallelism constructs to easily delegate the workload resulting from a workflow to a wide range of distributed computing environments. In this work, we briefly expose the strong assets of OpenMOLE and demonstrate its efficiency at exploring the parameter set of an agent simulation model. We perform a multi-objective optimisation on this model using computationally expensive Genetic Algorithms (GA). OpenMOLE hides the complexity of designing such an experiment thanks to its DSL, and transparently distributes the optimisation process. The example shows how an initialisation of the GA with a population of 200,000 individuals can be evaluated in one hour on the European Grid Infrastructure.

cs.DC↗

arXiv2015

Reliable Initialization of GPU-enabled Parallel Stochastic Simulations Using Mersenne Twister for Graphics Processors

Parallel stochastic simulations tend to exploit more and more computing power and they are now also developed for General Purpose Graphics Process Units (GP-GPUs). Conse-quently, they need reliable random sources to feed their applications. We propose a survey of the current Pseudo Random Numbers Generators (PRNG) available on GPU. We give a particular focus to the recent Mersenne Twister for Graphics Processors (MTGP) that has just been released. Our work provides empirically checked statuses designed to initialize a particular configuration of this generator, in order to prevent any potential bias introduced by the parallelization of the PRNG.

cs.DC↗

arXiv2015

Warp-Level Parallelism: Enabling Multiple Replications In Parallel on GPU

Stochastic simulations need multiple replications in order to build confidence intervals for their results. Even if we do not need a large amount of replications, it is a good practice to speed-up the whole simulation time using the Multiple Replications In Parallel (MRIP) approach. This approach usually supposes to have access to a parallel computer such as a symmetric mul-tiprocessing machine (with many cores), a computing cluster or a computing grid. In this paper, we propose Warp-Level Parallelism (WLP), a GP-GPU-enabled solution to compute MRIP on GP-GPUs (General-Purpose Graphics Processing Units). These devices display a great amount of parallel computational power at low cost, but are tuned to process efficiently the same operation on several data, through different threads. Indeed, this paradigm is called Single Instruction, Multiple Threads (SIMT). Our approach proposes to rely on small threads groups, called warps, to perform independent computations such as replications. We have benchmarked WLP with three different models: it allows MRIP to be computed up to six times faster than with the SIMT computing paradigm.

cs.DC↗

arXiv2014

How to Correctly Deal With Pseudorandom Numbers in Manycore Environments - Application to GPU programming with Shoverand

Stochastic simulations are often sensitive to the source of randomness that character-izes the statistical quality of their results. Consequently, we need highly reliable Random Number Generators (RNGs) to feed such applications. Recent developments try to shrink the computa-tion time by relying more and more General Purpose Graphics Processing Units (GP-GPUs) to speed-up stochastic simulations. Such devices bring new parallelization possibilities, but they also introduce new programming difficulties. Since RNGs are at the base of any stochastic simulation, they also need to be ported to GP-GPU. There is still a lack of well-designed implementations of quality-proven RNGs on GP-GPU platforms. In this paper, we introduce ShoveRand, a frame-work defining common rules to generate random numbers uniformly on GP-GPU. Our framework is designed to cope with any GPU-enabled development platform and to expose a straightfor-ward interface to users. We also provide an existing RNG implementation with this framework to demonstrate its efficiency in both development and ease of use.

cs.DC↗