MONTAGNAT , Johan

Medical images analysis today requires high end computing infrastructures to face the growing need for computing power and distributed medical data management. Medical applications increasingly require the federation of large data sets distributed over the image acquisition centers and their processing (e.g. for epidemiological studies,...

The segmentation of abdomen organs in volumetric medical images is difficult due to noisy and low contrasted images. Classical segmentation technics based on edge detection or thresholding lead to poor results. In this report, we use deformable meshes to perform segmentation. By using a template of the desired organ in our segmentation scheme,...

Production grids exhibit high failure rates ham- pering the development of many large scale scientific ap- plications. End users require robust experiment production environments ensuring efficient resubmission of failed tasks. Proper parameterization of resubmission strategies is a com- plex problem that depends on the non-stationary workload...

In this paper we propose to achieve a semantic equivalence between a visual- and a script-based workflow development paradigm. We accomplish this by building a script language which execution semantics matches an existing sophisticated, data-parallel scientific workflow language and its underlying GUI-based core workflow enactor. This...

The aim of this work is to automatically extract quantitative parameters from time sequences of 3D images (4D images) suited to heart pathology diagnosis. In this paper, we propose a framework for the reconstruction of the left ventricle motion from 4D images based on 4D deformable surface models. These 4D models are represented as a time...

Dans le cadre d'études de cohortes de patients, les neurosciences computationnelles sont confrontées à la manipulation de volumes de données toujours plus importants et généralement distribués, ainsi qu'à la complexité de leurs taritements. De plus, il est en général difficile de remonter à la source des éventements ayant conduit à l'échec...

WORKS'14 was the ninth workshop in the WORKS series. The call for papers attracted thirteen submissions from Europe, the USA and Russia. After peer reviews by the program committee, ten of the papers were accepted, covering a variety of topics: workflows scheduling, large-scale workflows optimization, languages, enactors, and support...

International audience

In this paper, the expressiveness of the simple Scufl data-flow language is studied by showing how it can be used to implement Turing machines. To do that, several non trivial Scufl patterns such as self-looping or sub-workflows are required and we precisely explicit them. The main result of this work is to show how a complex workflow can be...

Grids are key technologies to federate data distributed in multiple health institutions, thus enabling large scale multi-centric studies. However, the take up of these technologies is slow due to the difficulty to manipulate sensitive medical data in an open environment and the recognized risk of federated sites to loose control over their...

Deformable contours are now widely used in image segmentation, using different models, criteria and numerical schemes. Some theoretical comparisons between some deformable model methods have already been published. Yet, very few experimental comparative studies on real data have been reported. In this paper,we compare a levelset with a B-spline...

WORKS'13 was the eighth workshop in the WORKS series. The call for papers attracted sixteen submissions from Asia, Europe, North and South America. The quality of the papers, peer reviewed by the program committee, were exceptional this year and overall thirteen of the papers were accepted, covering a variety of topics, including provenance and...

WORKS'11 was the sixth issue in the WORKS workshop series. The call for papers attracted 23 submissions from Europe, North and South America. The program committee accepted 15 papers that cover a variety of topics, ranging from large-scale execution management of workflows (scalability, fault-tolerance, performance, optimization, etc) to...

WORKS'12 was the seventh issue in the WORKS workshop series. The call for papers attracted 14 submissions from Europe, North and South America. The program committee accepted 12 papers that cover a variety of topics, including data-driven workflows modeling, workflow systems scalability, performance and fault-tolerance, execution monitoring,...

An increasing number of scientific experiments are"in-silico": carried out at least partially using computers. Scientific Workflows have become a key tool to model and implement such experiments, but they tangle domain knowledge, tech- nical know-how and non-functional concerns and are, as a result, difficult to understand, reuse or repurpose....

This year is special for the WORKS series as this corresponds to the tenth issue of this scientific event dedicated to scientific workflows. The call for papers attracted thirteen submissions from Europe, the USA, India and Mexico. After peer reviews by the program committee, nine of the papers were accepted, covering a variety of topics:...

Cloud computing infrastructures are providing re- sources on demand for tackling the needs of large-scale dis- tributed applications. Determining the amount of resources to allocate for a given computation is a difficult problem though. This paper introduces and compares four automated resource allocation strategies relying on the expertise...

Production-grid users experience many system faults as well as high and variable latencies due to the scale, complexity and sharing of such infrastructures. To improve performance, they adopt different submission strategies, that are potentially aggressive for the infrastructure. This work studies the impact of three different strategies. It is...

This paper presents a method to optimize the timeout value of grid computing jobs. It relies on a model of the job execution time that considers the job management system latency through a random variable. It also takes into account a proportion of outliers to model either reliable clusters or production grids characterized by faults causing...

The problem we address in this paper is to build complex applications by reusing and assembling scientific codes on a production grid infrastructure. We first review the two main paradigms for executing application code on a grid: (a) the task based approach, associated to global computing, characterized by its efficiency, and (b) the service...

This paper presents a method to optimize the timeout value of grid computing jobs. It relies on a model of the job execution time that considers the job management system latency through a random variable. It also takes into account a proportion of outliers to model either reliable clusters or production grids characterized by faults causing...

Production grids have a potential for parallel execution of a very large number of tasks but also introduce a high overhead that significantly impacts the execution of short tasks. In this work, we present a strategy to optimize the partitioning of jobs on a grid infrastructure. This method takes into account the variability and the difficulty...

Today there are many different scientific Grid workflow man- agement systems using a wide array of custom workflow languages. Some of them are geared towards a data-based view, some are geared towards a control-flow based view and others try to be as generic, and therefore often com- plex, as possible. All of these languages and custom work-...

Workflow engines are powerful tools to implement data- intensive scientific applications exploiting parallel grid resources transparently. We discuss the advantages of impelmenting applications as workflows of services when dealing with large data sets. We show how the graph of services associated with data composition operators enable the...

This paper presents a method to optimize the timeout value of computing jobs. It relies on a model of the job execution time that considers the job management system latency through a random variable. It also takes into ac- count a proportion of outliers to model either reliable clus- ters or production grids characterized by faults causing...