Distributed medical images analysis on a Grid infrastructure

Bellotti, R.; Cerello, Piergiorgio; Tangaro, Sabina; Bevilacqua, Vitoantonio; Castellano, M.; Marra, Giuseppe; Carlo, Francesco De; Bagnasco, S.; Bottigli, U.; Cataldo, Rosella; Catanzariti, Ezio; Cheran, S. C.; Delogu, Pasquale; Mitri, I. De; Nunzio, Giorgio De; Fantacci, Maria Evelina; Fauci, F.; Gargano, G.; Golosio, Bruno; Indovina, Pietro Luigi; Lauria, A.; Torres, E. López; Magro, R.; Masala, G. L.; Massafra, Raffaella; Oliva, Piernicola; Martinez, A. Preite; Quarta, Maurizio; Raso, G.; Retico, Alessandra; Sitta, M.; Stumbo, S.; Tata, A.; Squarcia, S.; Schenone, Andrea; Molinari, Elisa; Canesi, Barbara

doi:10.1016/j.future.2006.07.006

Cited by 26 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MAGIC-5 project [13], [14] aims at developing Computer Aided Detection (CAD) software systems for Medical Applications on distributed databases by means of a grid infrastructure approach. The project deals with images from various medical fields (mammography, lung CT, brain MRI).…”

Section: Existing Systemsmentioning

confidence: 99%

Overview of Medical Data Management Solutions for Research Communities

Camarasu-Pop

Cervenansky

Cardenas

et al. 2010

2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing

View full text Add to dashboard Cite

International audienceMedical imaging research deals with large, heterogeneous and fragmented amounts of medical images. The need for secure, federated and functional medical image databases is very strong within these research communities. This paper provides an overview of the different projects concerned with building medical image databases for medical imaging research. It also discusses the characteristics and requirements of this community and tries to determine to what extent existing solutions can answer these specific requirements

show abstract

Section: Existing Systemsmentioning

confidence: 99%

Overview of Medical Data Management Solutions for Research Communities

Camarasu-Pop

Cervenansky

Cardenas

et al. 2010

2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing

View full text Add to dashboard Cite

show abstract

“…1 15 (vi) = 125 E Xi ,Yi,zi=-2,2 1 (xi, Yi, zd (10) The number of generated ants can be an integer in the (1,26) interval: the actual number Noffspring is determined assuming that it linearly depends on 1 5 , with Noffspring = 0(26) corrsponding to 1 5 = 1 5 ,min(1 5 ,max) respectively: In case N Of f spring is larger than the number of free neighbours Nfree, it is set to Nfree.…”

Section: Deploying the Modelmentioning

confidence: 99%

“…The approach we propose, called Channeler Ant Model, is a stable and elegant solution that requires little tuning (parameter-wise), provides an excellent performance on images with different dynamic ranges and noise levels and opens a multitude of possibilities for further research. The present work was carried on within the MAGIC-5 Project [10], focused on the development of algorithms for the automated detection of anomalies in medical images. The Channeler Ant Model discussed here will be adopted as a tool for the analysis of lung CT scans, so as to segment and remove the background coming from the bronchial and vascular trees in the lungs, which is the biggest source of false positives in the automated search for nodules.…”

mentioning

confidence: 99%

The Channeler Ant Model: Object segmentation with virtual ant colonies

Cerello

Cheran

Bagagli

et al. 2008

2008 IEEE Nuclear Science Symposium Conference Record

View full text Add to dashboard Cite

3-D object segmentation is an important and challenging topic in computer vision that could be tackled with artificial life models. A Channeler Ant Model (CAM), based on the natural ant capabilities of dealing with 3-D environments through self-organization and emergent behaviours, is proposed. Ant colonies, defined in terms of moving, pheromone laying, reproduction, death and deviating behaviours rules, is able to segment artificially generated objects of different shape, intensity, background. The model depends on few parameters and provides an elegant solution for the segmentation of 3-D structures in noisy environments with unknown range of image intensities: even when there is a partial overlap between the intensity and noise range, it provides a complete segmentation with negligible contamination (i.e., fraction of segmented voxels that do not belong to the object).

show abstract

“…Several works have been published, in the past years, for what was the golden example: mammography [3,4]. In that case, a very large population is subject to screening and it was natural to address the problem of a common infrastructure for the data analysis.…”

Section: Introductionmentioning

confidence: 99%

Analysis of medical images: the MAGIC-5 Project

Cerello¹

2011

Proceedings of 13th International Workshop on Advanced Computing and Analysis Techniques in Physics Research — PoS(ACAT2010)

View full text Add to dashboard Cite

The MAGIC-5 Project focuses on the development of analysis algorithms for the automated detection of anomalies in medical images, compatible with the use in a distributed environment. Presently, two main research subjects are being addressed: the detection of nodules in low-dose high-resolution computed tomographies of the lung and the analysis of brain MRIs for the segmentation and classification of the hyppocampus as an early marker of the Alzheimer's disease. MAGIC-5 was started by a community of high energy physics software developers, still in constant contact with -some of them also involved in -HEP projects. Some of the MAGIC-5 results, obtained with a newly developed model based on virtual ant colonies for the segmentation of complex structures, will be presented and discussed. The project takes advantage of a close collaboration with representatives of the medical community, that set requirements in terms of performance and functionality. Future developments are focusing more and more on the analysis of neuroimages, trying to exploit at best the huge amount of morphological and functional information generated by MRI and PET imaging.

show abstract

Distributed medical images analysis on a Grid infrastructure

Cited by 26 publications

References 20 publications

Overview of Medical Data Management Solutions for Research Communities

Overview of Medical Data Management Solutions for Research Communities

The Channeler Ant Model: Object segmentation with virtual ant colonies

Analysis of medical images: the MAGIC-5 Project

Contact Info

Product

Resources

About