Partial volume effect detection in MRI segmentation based on approximate decision reducts

• Autorzy: Widz S.
• Języki publikacji: EN

Abstrakty

EN

Segmentation of Magnetic Resonance Imaging (MRI) is a process of assigning tissue class labels to voxels. One of the main sources of segmentation error is the partial volume effect (PVE) which occurs most often with low resolution images - with large voxels, the probability of a voxel containing multiple tissue classes increases. We propose a multistage algorithm for segmenting MRI images with a mid-stage of recognizing the PVE voxels. The information about PVE regions added to other voxels features extracted from the image can increase the overall accuracy of the segmentation. In our methods we have utilize a classification approach based on approximate decision reducts derived from the data mining paradigm of the theory of rough sets. An approximate reduct is an irreducible subset of features, which enables to classify decision concepts with a satisfactory degree of accuracy in the training data. The ensembles of best found reducts trained for appropriate approximation degrees are applied to detection of the PVE and performing the segmentation.

Słowa kluczowe

EN

MRI Segmentation; PVE; rough sets; approximate decision reducts

PL

segmentacja obrazów MRI; PVE; zbiory przybliżone

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2007
• Tom: Vol. 11
• Strony: 227--233
• Opis fizyczny: Bibliogr. 19 poz., rys.

Twórcy

autor

Widz S.

• Polish – Japanese Institute of Information Technology, Koszykowa 86, 02-008 Warszawa, Poland

Bibliografia

• [1] CÁRDENES R, WARFIELD S.K., MACIAS E.M., SANTANA J.A., RUIZ-ALZOLA J., An Efficient Algorithm for Multiple Sclerosis Segmentation from Brain MRI. In: Moreno-Díaz R. and Pichler F., editors, EUROCAST, volume 2809 of Lecture Notes in Computer Science, pp. 542–551. Springer, 2003.
• [2] COCOSCO C.A., ZIJDENBOS A.P., EVANS A.C., Automatic Generation of Training Data for Brain Tissue Classification from MRI. In: Dohi T. and Kikinis R., editors, MICCAI (1), volume 2488 of Lecture Notes in Computer Science, pp. 516–523. Springer, 2002.
• [3] COLLINS D.L., ZIJDENBOS A.P., KOLLOKIAN V., SLED J.G., KABANI N.J., HOLMES C.J., EVANS A.C., Design and Construction of a Realistic Digital Brain Phantom. IEEE Trans. Med. Imaging, 17(3): pp. 463–468, 1998.
• [4] DUGAS-PHOCION G., BALLESTER M.Á.G., MALANDAIN G., AYACHE N., LEBRUN C., CHANALET S., BENSA C., Hierarchical Segmentation of Multiple Sclerosis Lesions in Multi-Sequence MRI. In: Proceedings of the 2004 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Arlington, VA, USA, 15-18 April 2004, pp. 157–160. IEEE, 2004.
• [5] KWAN R.K.S., EVANS A.C., PIKE G.B., An Extensible MRI Simulator for Post-Processing Evaluation. In: Höhne K.H. and Kikinis R., editors, VBC, volume 1131 of Lecture Notes in Computer Science, pp. 135–140. Springer, 1996.
• [6] KWAN R.K.S., EVANS A.C., PIKE G. B., MRI Simulation Based Evaluation and Classifications Methods. IEEE Trans. Med. Imaging, 18(11): pp. 1085–1097, 1999.
• [7] LAWRENCE D.. Handbook of Genetic Algorithms. Van Nostrand Reinhold, 1991.
• [8] PAWLAK Z.. Rough Sets: Theoretical Aspects of Reasoning about Data. Kluwer Academic Publishers, Norwell, MA, USA, 1992.
• [9] PAWLAK Z., SKOWRON A.. Rudiments of Rough Sets. Inf. Sci., 177(1):pp. 3–27, 2007.
• [10] ŚLĘZAK D., Approximate Entropy Reducts. Fundam. Inform., 53(3-4): pp.365–390, 2002.
• [11] ŚLĘZAK D., Multi-Attribute Dependencies: The Case Study of Association Reducts. Plenary lecture at the International Conference on Rough Sets and Emerging Intelligent Systems Paradigms, RSEISP’2007, Warsaw, Poland
• [12] ŚLĘZAK D., WIDZ S., Approximation degrees in decision reduct classifiers for noisy data. In prep., 2007.
• [13] ŚLĘZAK D., WRÓBLEWSKI J., Order Based Genetic Algorithms for the Search of Approximate Entropy Reducts. In: Proc. RSFDGrC’2004, Chongqing, China, pp. 308-311. Springer (2003)
• [14] ŚLĘZAK D., ZIARKO W., Attribute Reduction in the Bayesian Version of Variable Precision Rough Set Model. In: Proc. of RSKD’2003 Elsevier, ENTCS, 82(4), (2003)
• [15] ŚLĘZAK D., ZIARKO W., The investigation of the Bayesian Rough Set Model. International Journal Approximate Reasoning, 40(1-2) pp. 81–91, 2005.
• [16] WIDZ S., REVETT K., ŚLĘZAK D., A Hybrid Approach to MR Imaging Segmentation Using Unsupervised Clustering and Approximate Reducts. In: Proc: RSFDGrC’2005 (2), Regina, Canada, Springer (2005) pp.372–382
• [17] WIDZ S., REVETT K., ŚLĘZAK D., A Rough Set-Based Magnetic Resonance Imaging Partial Volume Detection System. In: Proc. PReMI’2005, Calcutta, India, Springer (2005) pp. 756–761.
• [18] WIDZ S. ŚLĘZAK D., Approximation Degrees in Reduct-Based MRI Segmentation, In Proc: FBIT’2007, Jeju-Do, Korea, 2007, in publish
• [19] WRÓBLEWSKI J., Theoretical foundations of order-based genetic algorithms. Fundamenta Informaticae 28(3-4) pp. 423–430, 1996.