Architecture de fusion de données basée sur la théorie de l’évidence pour la reconstruction d’une vertèbre
Structure of data fusion based on the theory of evidence for the reconstruction of vertebra
OPEN ACCESS
The work presented in this article is carried out in collaboration with the department of radiology of the «Institut Calot de Berck-sur-Mer » and Siemens. This article relates to the description of an architecture of data fusion for detection of the cortical osseous one of a vertebra from magnetic resonance imaging (MRI). The goal is to determine the effective membership of points of contour obtained by active contour method to the cortical. Several parameters associated to the points are taken into account (gray level, mean of gray leveland standard deviation on a neighbourhood, outdistances between points belonging to close slices). The architecture is based on the formalism of the evidence. We discuss the results obtained, the validity of them and we propose further objectives of this work.
Résumé
Cet article concerne la description d’une architecture de fusion de données pour la détection du cortical osseux d’une vertèbre dans une image IRM, développée dans le cadre d’une collaboration avec le département de radiologie de l’Institut Calot de Berck-sur-Mer et Siemens. Il s’agit de déterminer l’appartenance effective de points de contour obtenus par une méthode de segmentation par contour actif au cortical. Plusieurs paramètres associés à chacun de ces points sont pris en compte (niveau de gris, niveau de gris moyen et écart type sur un voisinage, distance entre points appartenant à des coupes voisines). L’architecture est basée sur le formalisme de la théorie de l’évidence. Nous discutons des résultats obtenus, de leur validité et nous donnons les perspectives envisagées de la suite de ce travail.
Data fusion, evidence theory (Dempster-Shafer), MRI images, 2D segmentation, snake
Mots clés
Fusion de données, théorie de l’évidence (Dempster-Shafer), images IRM, segmentation 2D, contour actif
[1] H. Leclet and P.M. Delforge, Des scolioses : quand et comment, Rev. Imagerie Medicale, n°5, pp. 773-782, 1993.
[2] P. Maroteaux, Les maladies osseuses de l’enfant, Édition Flammarion, 1995.
[3] A. Alaux, L’Image par Résonnance Magnétique, Édition Sauramps Médical, 1994.
[4] L. Gautier and A. Taleb-Ahmed and M. Rombaut and J.G. Postaire and H. Leclet, Proved segmentation from Pictures Sequence by Evidence Theory, Application MRI pictures, The 2nd International Conference on Information, Fusion 99, pp. 55-59, 1999.
[5] M. Brejl and M. Sonka, Medical Image segmentation, automated design of border detection criteria from examples, Jour. Electron. Imag., vol 8, n°1, pp. 54-64, 1999.
[6] L. Gautier and A. Taleb-Ahmed and M. Rombaut and J.G. Postaire and H. Leclet, Belief function in low level data fusion : Application in MRI, The 3rd International Conference on Information, Fusion 2000, pp. 5-9, 2000.
[7] A. Taleb-Ahmed and L. Gautier and M. Rombaut and J.G. Postaire, 2D segmentation of vertebra by Evidence Theory : Application on 2D slices of lumbar rachis MRI, The 4th International Conference on Information, Fusion 2001, pp. 12-16, 2001.
[8] I. Bloch, Information combination operators for data fusion : A comparative review with classification, IEEE Trans. on Systems, Man and Cybernetics, pp. 52-67, 1996.
[9] L.A. Klein, Sensor and data fusion concepts and applications, SPIE, Opt. Eng., vol 2059, pp. 48-54, 1993.
[10] D. Dubois and H. Prade, Possibility theory in information fusion, IEEE 3th Inter. Conf. on Information Fusion, pp. PS-6, 2000.
[11] M. Kunt, Traitement numérique des images, Édition Presses polytechniques et universitaires romandes, 1993.
[12] J.P. Cocquerez and S. Philipp, Analyse d’images : filtrage et segmentation, Édition Masson, 1995.
[13] G. Shafer, A mathematical theory of evidence, Édition Princeton University Press, 1976.
[14] A.P. Dempster, Upper and lower probability function in a context of uncertainty, Annals of math. statistics, vol 38, pp. 325-339, 1967.
[15] A.P. Dempster, A generalization of bayesian inference, Jour. of the Royal Statistical Society, vol 30, pp. 205-247, 1968.
[16] P. Smets and R. Kennes, The transferable belief model, Artificial Intelligence vol 66, pp. 191-234, 1994.
[17] P. Smets, The transferable belief model for quantified belief representation, Handbook of defeasible reasoning and uncertainty management systems. Eds D. Gabbay and P. Smets, vol 1, pp. 267-301, 1998.
[18] P. Smets, Data fusion in the transferable belief model, Proc. 3rd Intern. Conf. Information Fusion, Paris, pp. 21-33, 1994.
[19] D. Dubois and H. Prade, Théorie des possibilités : applications à la représentation des connaissances en informatique, Masson, 1988.
[20] D. Dubois and H. Prade, La fusion d’informations imprécises, Traitement du Signal et des Images, vol 11, n°6, pp. 447-458, 1994.
[21] E. Lefevre and O. Colot and P. Vannoorenberghe, Contribution des mesures d’information à la modélisation crédibiliste de connaissance, Traitement du Signal et des Images, vol 17, n°2, pp. 87-97, 2000.
[22] T. Denoeux, Analysis of evidence-theoretic decision rules for pattern classification, Pattern Recognition, vol 30, n°7, pp. 1095-1107, 1997.
[23] R. Terzopoulos and A. Witkin and M. Kass, Symmetry-seeking models for 3D object reconstruction, Int. Jour. of Com. Vision, pp. 211-221, 1987.
[24] M. Kass and A. Witkin and R. Terzopoulos, Snakes : Active contour models, pp. 312-331, Int Jour of Com Vision, 1988.
[25] L.D. Cohen and I. Cohen, A finite element methods for active contour models and ballon for 2D and 3D images, IEEE Trans Patt Anal and Mach Int 3th, pp. 1131-1147, 1993.
[26] K.F. Lai, Deformable contour : Modeling, Extraction, Detection and Classification, Ph.D thesis Wisconsin-Madison University, 1994.
[27] T. Abe and Y. Matsuzawa, Multiple active contour models with application to region extraction, 15th Inter. Conf. on Pattern Recognition, vol 4, Barcelona, pp. 634-637, 2000.
[28] D.M. Gavrila and L.S. Davis, Towards 3-d model-based tracking and recognition of human movement: a multi-view approach, In International Workshop on Automatic Face-and Gesture-Recognition. IEEE Computer Society, Zurich, 1995.
[29] L. Rabiner and B. Juang, Fundamentals of speech recognition, Englewood Cliffs, N.J, Prentice Hall, 1993.
[30] M. Schmill and T. Oates, Learned models for continuous planning, In Seventh International Workshop on Artificial Intelligence and Statistics, 1999.
[31] K. Gollmer and C. Posten, Detection of distorted pattern using dynamic timewarping algorithm and application for supervision of bioprocesses, On-Line Fault Detection and Supervision in the Chemical Process Industries Edited by: Morris A.J., Martin E.B., 1995.
[32] E.G. Caiani and A. Porta and G. Baselli, Warped-average template technique to track on a cycleby-cycle basis the cardiac filling phases on left ventricular volume, IEEE Computers in Cardiology. vol 25 Cat. n°98 CH36292, NY, USA, 1998.