Automated Multi-Contrast Brain Pathological Area Extraction from 2D MR Images

 

P. Dvorak*¹, K. Bartusek², W. G. Kropatsch³ and Z. Smékal⁴

 

^1,2 Institute of Scientific Instruments of the ASCR, v.v.i. Academy if Sciences of the Czech Republic Brno, Czech Republic * pavel.dvorak@phd.feec.vutbr.cz

^1,4 Dept. of Telecommunications Faculty of Electrical Engineering and Communication Brno University of Technology Brno, Czech Republic.

³ Pattern Recognition and Image Processing Group Institute of Computer Graphics and Algorithms Faculty of Informatics Vienna University of Technology Vienna, Austria.

 

ABSTRACT

The aim of this work is to propose the fully automated pathological area extraction from multi-parametric 2D MR images of brain. The proposed method is based on multi-resolution symmetry analysis and automatic thresholding. The proposed algorithm first detects the presence of pathology and then starts its extraction. T2 images are used for the presence detection and the multi-contrast MRI is used for the extraction, concretely T2 and FLAIR images. The extraction is based on thresholding, where Otsu's algorithm is used for the automatic determination of the threshold. Since the method is based on symmetry, it works for both axial and coronal planes. In both these planes of healthy brain, the approximate left-right symmetry exists and it is used as the prior knowledge for searching the approximate pathology location. It is assumed that this area is not located symmetrically in both hemispheres, which is met in most cases. The detection algorithm was tested on 203 T2-weighted images and reached the true positive rate of 87.52% and true negative rate of 93.14%. The extraction algorithm was tested on 357 axial and 443 coronal real images from publicly available BRATS databases containing 3D volumes brain tumor patients. The results were evaluated by Dice Coefficient (axial: 0.85±0.11, coronal 0.82±0.18) and by Accuracy (axial: 0.96±0.05, coronal 0.94±0.09).

Keywords: Brain Pathology, Brain Tumor, MRI, Multi-contrast MRI, Symmetry Analysis.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Acknowledgements

Research described in this paper was financed by the National Sustainability Program under grant LO1401, by the Czech Science Foundation under grant no. 102/12/1104, and by the Czech Ministry of Education under grant no. LD14091. For the research, infrastructure of the SIX Center was used.

 

References

[1] Y. Hernandez-Heredia, J.M. González-Linares, N. Guil, J. Ortiz, R. Hernandez, J.R. Cózar, "Object Detection with Vocabularies of Space-time Descriptors", Journal of Applied Research and Technology (JART) 10(6), 2012, pp. 950-956.         [ Links ]

[2] I. López-Juárez, M. Castelán, F.J.Castro-Martínez, M. Peña-Cabrera, R.Osorio-Comparan, "Using Object's Contour, Form and Depth to Embed Recognition Capability into Industrial Robots", Journal of Applied Research and Technology (JART) 11(1), 2013, pp. 5-17.         [ Links ]

[3] J. Mikulka, and E. Gescheidtova, "An Improved Segmentation of Brain Tumor, Edema and Necrosis." Proceedings of PIERS 2013, Taipei. 2013. pp. 25-28. ISBN: 978-1-934142-24-0.         [ Links ]

[4] Y. Wu et al. "Semi-automatic Segmentation of Brain Tumors Using Population and Individual Information", J. Digital Imaging 26(4), 2013 pp. 786-796.         [ Links ]

[5] V. Pedoia et al., "Glial brain tumor detection by using symmetry analysis," CProc. SPIE 8314, Medical Imaging 2012: Image Processing, 831445. February 23, 2012.         [ Links ]

[6] B. N. Saha et al., "Quick detection of brain tumors and edemas: A bounding box method using symmetry", Computerized Medical Imaging and Graphics, Vol. 36, Is. 2, March, 2012, pp. 95-107, ISSN 0895-6111.         [ Links ]

[7] N. Zhanga et al., "Kernel feature selection to fuse multi-spectral MRI images for brain tumor segmentation," in CVIU, vol. 115(2), 2011, pp. 256-269.         [ Links ]

[8] S. Ruan et al. "Tumor segmentation from a multispectral MRI images by using support vector machine classification", In International Symposium on Biomedical Imaging, Washington, USA, 2007. pp. 1236-1239.         [ Links ]

[9] W. Dou et al., "A framework of fuzzy information fusion for segmentation of brain tumor tissues on MR images", Image and Vision Computing 25, 2007, pp. 164-171.         [ Links ]

[10] J.J. Corso et al., "Multilevel segmentation and integrated Bayesian model classification with an application to brain tumor segmentation", in: MICCAI2006, Copenhagen, Denmark, Lecture Notes in Computer Science, Vol. 4191, Springer, Berlin, October 2006, pp. 790-798.         [ Links ]

[11] S. Ho, E. Bullitt, G. Gerig, "Level set evolution with region competition: automatic 3D segmentation of brain tumors", ICPR, Quebec, August, 2002, pp. 532-535. Automated Multi-Contrast Brain Pathological Area Extraction from 2D MR Images, P. Dvorák et al. / 58-69        [ Links ]

[12] J. Mikulka et al., "Soft-tissues image processing: Comparison of traditional segmentation methods with 2D active contour methods," Measurement Science Review, vol. 12, num. 4, pp. 153-161, 2012.         [ Links ]

[13] M. Cap et al., "Automatic Detection and Segmentation of the Tumor Tissue.'' In Proceedings of PIERS 2013", Taipei, 2013. pp. 53-56. ISBN: 978-1-934142-24-0.         [ Links ]

[14] A.Rajendran and R. Dhanasekaran, " Fuzzy Clustering and Deformable Model for Tumour Segmentation on MRI Brain Image: A Combined Approach", Procedia Engineering, Vol. 30, 2012, pp. 327 -333.         [ Links ]

[15] S. Taheri et al, "Threshold-based 3D tumor segmentation using level set (TSL)", In IEEE Workshop on Applications of Computer Vision (WACV 07), Texas, USA, 2007, pp. 45-51.         [ Links ]

[16] R. Benes et al. "Automatically designed machine vision systém for the localization of CCA transverse section in ultrasound images", Computer Methods and Programs in Biomedicine. 2013, 109(3). pp. 92-103, ISSN 0169-2607.         [ Links ]

[17] A. S. Capelle et al., "Evidential segmentation scheme of multi-echo MR images for the detection of brain tumors using neighborhood information," Information Fusion. vol. 5, 2004, pp. 103-216.         [ Links ]

[18] V. Uher et al. "3D Brain Tissue Selection and Segmentation from MRI", In 36th International Conference on Telecommunications and Signal processing. Roma, Italy, 2013. pp. 839-842. ISBN: 9781-4799-0402-0.         [ Links ]

[19] E. R. Arce-Santana and Alfonso Alba, "Image registration using Markov random coefficient and geometric transformation fields," Pattern Recognition, Vol. 42, Is. 8, August, 2009, pp. 1660-1671, ISSN 0031-3203.         [ Links ]

[20] S. Karuppanagounder and K. Thiruvenkadam, "A Novel Technique for Finding the Boundary between the Cerebral Hemispheres from MR Axial Head Scans", Proceeding of: Proceedings of the 4th Indian International Conference on Artificial Intelligence, IICAI 2009, Tumkur, Karnataka, India, December 16-18, pp.~1486-1502, 2009.         [ Links ]

[21] A. Bhattacharyya, "On a measure of divergence between two statistical populations defined by their probability distribution", Bulletin of the Calcutta Mathematical Society, vol.~35, pp. 99-110, 1943.         [ Links ]

[22] W. G. Kropatsch et al., "Multiresolution Image Segmentations in Graph Pyramids," Applied Graph Theory in Computer Vision and Pattern Recognition Studies in Computational Intelligence, vol. 52, pp. 3-41, 2007.         [ Links ]

[23] P. Dvorak et al., "Automated Segmentation of Brain Tumor Edema in FLAIR MRI Using Symmetry and Thresholding". in PIERS 2013 Stockholm Proceedings. Stockholm, Sweden, August, 2013. pp. 936-939. ISBN: 978-1-934142-26-4.         [ Links ]

[24] C. Cortes and V. N. Vapnik, "Support-Vector Networks", Machine Learning, vol. 20, Issue 3, pp. 271297, September, 1995.         [ Links ]

[25] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, No. 1, 1979, pp. 62-66.         [ Links ]

[26] C. A. Cocosco et al, "BrainWeb: Online interface to a 3d MRI simulated brain database", NeuroImage, 5(4), 1997.         [ Links ]

[27] M. Prastawa et al., "Simulation of Brain Tumors in MR Images for Evaluation of Segmentation Efficacy", Med Image Anal. 13(2), April, 2009, pp. 297-311.         [ Links ]

[28] L. R. Dice, "Measures of the amount of ecologic association between species". Ecology 1945;26:297-302.         [ Links ]

[29] A. Zijdenbos B. Dawant, "Brain segmentation and white matter lesion detection in MR images". Crit Rev Biomed Eng 1994;22.         [ Links ]

[30] A. Hadjiprocopis et al., "Unbiased segmentation of diffusion-weighted magnetic resonance images of the brain using iterative clustering", Magnetic Resonance Imaging 23 (2005) 877-885.         [ Links ]