Automatic Identification of Regions of Interest on Renal Tomographic Images. Identification Automatique des Régions D’Intérêts sur des Images Tomographiques Rénales

Automatic Identification of Regions of Interest on Renal Tomographic Images

Identification Automatique des Régions D’Intérêts sur des Images Tomographiques Rénales

Djamal Boukerroui Wala Touhami  Jean-Pierre Cocquerez 

Université de Technologie de Compiègne, CNRS UMR 6599 Heudiasyc BP 20529 - 60205 Compiègne Cedex, France

École Nationale d’Ingénieurs de Tunis BP 37, Le Belvedere 1002 Tunis

Page: 
239-254
|
Received: 
18 June 2008
| |
Accepted: 
N/A
| | Citation

OPEN ACCESS

Abstract: 

We propose, in this paper, an original approach in a statistical framework, for fully automatic delineation of kidneys (healthy and pathological) in 2D CT images. Our approach has two main steps : a localisation step followed by a delineation step. The localisation step is guided by a statistically learned prior spatial model in one hand and a grey level prior model in a second hand. The second step, utilizes the localisation results in order to precisely delineate the kidney’s regions using a set of learned IF-THEN rules. The proposed approach is tested on clinically acquired images and promising results are obtained.

Résumé

Nous proposons, dans le présent papier, une approche originale dans un cadre statistique pour l’identification automatique des reins (sains et pathologiques) sur des images tomographiques bidimensionnelles (CT). Notre approche est constituée de deux phases : une phase de localisation suivie d’une phase de délimitation. La phase de localisation est guidée, d’une part, par un modèle a priori spatial et d’autre part, par un modèle a priori sur les niveaux de gris, statistiquement appris. La seconde phase consiste à utiliser les résultats de la localisation afin de délimiter la région du rein en utilisant un ensemble de règles. Cette approche est testée sur des images cliniquement acquises et des résultats satisfaisants sont obtenus.

Keywords: 

Automatic detection, statistical approach, prior models, kidney cysts, CT.

Mots clés

Détection automatique, approche statistique, modèles a priori, kyste de rein, CT.

1. Introduction
2. Architecture Globale de l’Approche Proposée
3. Phase de Localisation des Reins
4. Phase de Délimitation du Rein
5. Résultats
6. Discussion des Cas d’Échec
7. Conclusion
  References

[1] N. ARCHIP, P.J. ERARD, M. EGMONT-PETERSEN, J.M. HAEFLIGER, and J.F. GERMOND, A knowledge-based approach to automatic detection of the spinal cord in CT images, IEEE Trans. Med. Imag., 21(12) : 1504-1516, December 2002.

[2] J. BESAG. On the statistical analysis of dirty pictures, Journal of the Royal Statistical Society. Series B, 48(3) : 259–302, 1986.

[3] D. BOUKERROUI, A. BASKURT, J.A. NOBLE, and O. BASSET, Segmentation of ultrasound images – multi-resolution 2D and 3D algorithm based on global and local statistics, Pattern Recognition Letters, 24(4-5) : 779-790, February 2003.

[4] Djamal BOUKERROUI, Wala TOUHAMI, and Jean-Pierre COCQUEREZ, Automatic regions of interest identification and classification in CT images : Application to kidney cysts. In First Workshops on Image Processing Theory, Tools and Applications, pages 257–264, 2008.

[5] L. BREIMAN, J.H. FRIEDMAN, R.A. OLSHEN, and C.J. STONE. Classification And Regression Trees, Belmont, CA, 1983.

[6] O. CAMARA, O. COLLIOT, and I. BLOCH. Computational modeling of thoracic and abdominal anatomy using spatial relationships for image segmentation, Real-Time Imaging, 10(4) : 263-273, 2004.

[7] Olivier COMMOWICK, Vincent ARSIGNY, Aurélie ISAMBERT, Jimena COSTA, Frédéric DHERMAIN, François BIDAULT, Pierre-Yves BONDIAU, Nicholas AYACHE, and Grégoire MALANDAIN, An efficient locally affine frame-work for the smooth registration of anatomical structures, Medical Image Analysis, 12(4) : 427-441, 2008.

[8] T.T. COOTES, A. HILL, C.J. TAYLOR, and J. HASLAM, The use of active shape models for locating structures in medical images, Image and Vision Computing, 12(6) : 355-366, July 1994.

[9] T.T. COOTES, C.J. TAYLOR, D.H. COOPER, and J. GRAHAM, Active shape models – their training and application, Computer Vision and Image Understanding, 61(1) : 38–59, January 1995.

[10] D. CREMERS, S.J. OSHER, and S. SOATTO. Kernel density estimation and intrinsic alignment for shape priors in level set segmentation, International Journal of Computer Vision, 69(3) : 335-351, 2006.

[11] Daniel CREMERS, Mikael ROUSSON, and Rachid DERICHE, A review of statistical approaches to level set segmentation : Integrating color, texture, motion and shape, International Journal of Computer Vision, 72(2) :195-215, April 2007.

[12] R. D’ÁGOSTINO and M. STEPHENS, Goodness-of-fit techniques, Marcel Dekker, NY, USA, 1986.

[13] A. P. DEMPSTER, N. M. LAIRD, and D. B. RUBIN, Maximum likelihood from incomplete data via the EM algorithm, Journal of the Royal Statistical Society, Series B, 34 : 1-38, 1977.

[14] E. W. DIJKSTRA, A note on two problems in connexion with graphs. Numerische Mathematik, 1 : 269-271, 1959.

[15] J. DUNCAN and N. AYACHE, Medical image analysis : Progress over two decades and the challenges ahead, IEEE Trans. Pattern Anal, Mach. Intell., 22(1) : 85-106, 2000.

[16] Igor DYDENKO, Fadi JAMAL, Olivier BERNARD, Jan D’HOOGE, Isabelle E. MAGNIN, and Denis FRIBOULET, A level set framework with a shape and motion prior for segmentation and region tracking in echocardiography, Medical Image Analysis, 10(2) : 162-177, April 2006.

[17] M. GONDRAN and M. MINOUX, Graphes et algorithmes, Eyrolles, 1ère édition edition, 1995.

[18] J. V. HAJNAL, D.L.G. HILL, and D.J. HAWKES, Medical image registration, CRC press, June 2001.

[19] T. KANEKO, Lixu GU, and H. FUJIMOTO, Abdominal organ recognition using 3D mathematical morphology. In Int. Conf. On Pattern Recognition, pages 263-266, Barcelona, Spain, 2000.

[20] L.J. KARSSEMEIJER, N. VAN ERNING and E.G. EIJKMAN, Recognition of organs in CT-image sequences : a model guided approach, Comput Biomed Res., 21(5) : 434-448, October 1988.

[21] M. KOBASHI and L.G. SHAPIRO, Knowledge-based organ identification from CT images. Pattern Recognition, 28(4) : 475-491, 1995.

[22] J.C. LAGARIAS, J. A. REEDS, M. H. WRIGHT, and P. E. WRIGHT, Convergence properties of the Nelder-Mead simplex method in low dimensions, SIAM Journal of Optimization, 9(1) : 112-147, 1998.

[23] C.C. LEE, P.C. CHUNG, and H.M. TSAI, Identifying multiple abdominal organs from CT image series using a multimodule contextual neural network and spatial fuzzy rules, IEEE Trans. Inf. Technol. Biomed., 7(3) : 208-217, 2003.

[24] M. LEVENTON, E. GRIMSON, and O. FAUGERAS, Statistical shape influence in geodesic active contours. In Proceedings of the IEEE Computer Vision on Pattern Recognition, volume 1, pages 316–323, Hilton Head, SC, USA, Jun 2000. IEEE Computer Society.

[25] D.-T. LIN, C.-C. LEI, and S.-W. HUNG, Computer-aided kidney segmentation on abdominal CT images, IEEE Trans. Inf. Technol. Biomed., 10(1) : 59-65, 2006.

[26] Grégoire MALANDAIN, Les mesures de similarité pour le recalage des images médicales, Habilitation à diriger des recherches, Université Nice Sophia-Antipolis, March 2006.

[27] A. MORENO, C.M. TAKEMURA, O. COLLIOT, O. CAMARA, and I. BLOCH. Using anatomical knowledge expressed as fuzzy constraints to segment the heart in CT images. Pattern Recognition Letters, 41(8) : 2525-2540, 2008.

[28] A. PAPOULIS and S. U. PILLAI, Probability, Random Variables and Stochastic Processes, McGraw-Hill, 4 edition edition, 2001.

[29] N. PARAGIOS, Y. CHEN, and O. FAUGERAS, Handbook of Mathematical Models in Computer Vision. Springer, (1st edition), October 31 2005.

[30] H. PARK, P.H. BLAND, and C.R. MEYER, Construction of an abdominal probabilistic atlas and its application in segmentation, IEEE Trans. Med. Imag., 22(4) : 483-492, February 2003.

[31] D.L. PHAM, C. XU, and J.L. PRINCE, Current methods in medical image segmentation. Annual Review of Biomedical Engineering, 2: 315-337, August 2000.

[32] W.H. PRESS, S.A. TEUKOLSKY, W.T. VETTERLING, and B.P. FLANNERY, Numerical Recipes in C : The Art of Scientific Computing, Cambridge University Press, NY, 1992.

[33] R. QUINLAN. C4.5 : Programs for Machine Learning, San Diego, 1993.

[34] A. SHIMIZU, R. OHNO, T. IKEGAMI, H. KOBATAKE, S. NAWANO, and D. SMUTEK, Segmentation of multiple organs in non-contrast 3D abdominal CT images. Computer-Assisted Radiology and Surgery, 2(3-4) : 135-142, 2007.

[35] Martin SPIEGEL, Dieter A. HAHN, Volker DAUM, and JAKOB. Segmentation of kidneys using a new active shape model generation technique based on non-rigid image registration. Computerized Medical Imaging and Graphics, 33(1) : 29-39, 2009.

[36] K. SUZUKI, I. HORIBA, and N. SUGIE, Linear-time connected component labeling based on sequential local operations. Computer Vision and Image Understanding, 89(1) : 1-23, 2003.

[37] P. THÉVENAZ and M. UNSER, Optimization of mutual information for multiresolution image registration. IEEE Trans. Image Process., 9(12) : 2083-2099, December 2000.

[38] Wala TOUHAMI, Djamal BOUKERROUI, and Jean-Pierre COCQUEREZ, Fully automatic kidneys detection in 2D CT images : A statistical approach. In Medical Image Computing and Computer-Assisted Intervention, pages 262–269, 2005.

[39] Baigalmaa TSAGAAN, Akinobu SHIMIZU, Hidefumi KOBATAKE, and Kunihisa MIYAKAWA, An automated segmentation method of kidney using statistical information. In Medical Image Computing and Computer-Assisted Intervention, pages 556-563, 2002.

[40] A. TSAI,W. WELLS, C. TEMPANY, E. GRIMSON, and A. WILLSKY, Mutual information in coupled multi-shape model for medical image segmentation. Medical Image Analysis, 8(4) : 429-445, December 2004.

[41] A. TSAI, A. YEZZI, W. WELLS, C. TEMPANY, D. TUCKER, A. FAN, W.E. GRIMSON, and A. WILLSKY, A shape-based approach to the segmentation of medical imagery using levels sets. IEEE Trans. Med. Imag., 22(2) :137–154, February 2003.

[42] B. C. VEMURI,Y. CHENAND J. YE, and C. M. LEONARD, Image registration via level-set motion : Applications to atlas-based segmentation. Medical Image Analysis, 7(1) :1-20, March 2003.

[43] J. XIE,Y. JIANG, and H.T. TSUI, Segmentation of kidney from ultrasound images based on texture and shape priors. IEEE Trans. Med. Imag., 24(1) : 45-57, January 2005.

[44] Y. ZHANG, M. BRADY, and S. SMITH, Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans. Med. Imag., 20(1) : 45-57, January 2001.