ارزیابی بخش‌بندی توأم با تصحیح میدان بایاس تصاویر MR مغز انسان توسط روش‌های تنظیم سطح و مؤلفه‌های ذاتی ضرب‌شونده

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی برق، دانشگاه آزاد اسلامی، واحد علوم و تحقیقات، تبریز، ایران

2 دانشکده مهندسی پزشکی، دانشگاه صنعتی سهند، تبریز، ایران

چکیده

بخش‌بندی تصاویر MR مغز یک مساله مهم در محاسبات پردازش تصاویر پزشکی است. در این تصاویر، بخش‌بندی به‌وسیله یک عامل درونی به‌نام ناهمگنی شدت دچار خطا می‌گردد که این ناهمگنی به‌دلیل وجود هم‌پوشانی در بین شدت بافت‌های مغزی است و اغلب باعث کلاس‌بندی نادرست بافت‌های مغزی می‌گردد. در این مقاله دو روش پیشنهادی جهت بخش‌بندی و اصلاح بایاس این تصاویر مطرح می‌شود که از طریق دو الگوریتم تنظیم سطح (LSM) و بهینه‌سازی مؤلفه‌های ذاتی ضرب‌شونده (MICO) پیاده‌سازی می‌گردند. روش‌های مطرح‌شده در این مقاله عبارت‌اند از: اصلاح بایاس تصاویر MR مغز انسان توسط یکی از دو الگوریتم فوق و بخش‌بندی آن توسط الگوریتم دیگر و بالعکس. هدف، بررسی کارایی روال تصحیح بایاس و بخش‌بندی هر الگوریتم به‌صورت جدا و ارزیابی کمی و کیفی نتایج حاصله و انتخاب الگوریتم مناسب جهت به‌دست آوردن نواحی سه‌گانه بافت‌های مغزی (WM ،GM و CSF) است. تحلیل‌های کمی و کیفی بر روی نتایج، دقت بالای 90 درصدی را برای ناحیه حاوی CSF با استفاده از الگوریتم MICO و همچنین به همین میزان برای نواحی WM و GM توسط الگوریتم LSM را نشان داد. با استفاده از این نتایج می‌توان الگوریتم بهینه جهت اصلاح بایاس و بخش‌بندی هر ناحیه را انتخاب کرد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Evaluation of Segmentation and Bias Field Correction in MR Brain Images Using Level Set and Multiplicative Intrinsic Component Optimization Methods

نویسندگان [English]

  • A. Alipour Sifar 1
  • M. Shamsi 2
1 Faculty of Electrical Engineering, Islamic Azad University, Science & Research Branch, Tabriz, Iran
2 Faculty of Biomedical Engineering, Sahand University of Technology, Tabriz, Iran
چکیده [English]

Segmentation of brain MR images is a major issue in medical image processing computations. In these images, segmentation is failed by the existence of internal artifact which is called intensity inhomogeneity due to the existence of overlap effect among brain tissue intensities which often causes false classification of brain tissues. In this paper, two suggested methods for segmentation and bias field correction arises, which these images are implemented through the level set (LSM) and multiplicative intrinsic component (MICO) algorithms. Methods outlined in this article include: bias field correction of the human brain MR images by one of these algorithms and segmentation by other algorithm and vice versa. Quantitative and qualitative analysis on the final results showed, accuracy above 90% for the area containing the CSF using the MICO algorithm as well as the areas WM and GM by LSM algorithm. These results can be used to select efficient algorithm to correct the bias field and segmenting each area, separately.

کلیدواژه‌ها [English]

  • Level set algorithm
  • multiplicative intrinsic component optimization
  • bias field correction
  • segmentation
  • magnetic resonance images

مراجع

[1] W. Wells, E. Grimson, R. Kikinis, F. Jolesz, “Adaptiv segmentation of MRI data,” IEEE Trans, Med Imaging, vol. 15, no. 4, pp. 429-42, 1996.
[2] D. Pham, J. Prince, “Adaptive fuzzy segmentation of magnetic resonance imaging,” IEEE Trans, Med Imaging, vol. 18, no. 9, pp. 737-52, 1999.
[3] D. Pham, “Spatial model for fuzzy clustering,” Compute. Vis. Image Underst, vol. 84, no. 2, pp. 285-97, 2001.
[4] B. Johnston, M.S. Atkins, B. Mackiewich, M. Anderson, “Segmentation of multiple sclerosis lesions in intensity correct multispectral MRI,” IEEE Trans, Med Imaging, vol. 15, no. 2 pp. 154-69, 1996.
[5] J. Sled, A. Zijdenbos, A. Evans, “A nonparametric method for automatic correction of intensity nonuniformity in MRI data,” IEEE Trans, Med Imaging, vol. 17, no. 1, pp. 87-97, 1998.
[6] V. Leemput, K. Maes, D. Vandermeulen, P. Suetens, “Automated model-based bias field correction of MR images of the brain,” IEEE Trans, Med Imaging, vol. 18, no. 10, pp. 885-96, 1999.
[7] M. Styner, C. Brechbuhler, G. Szekely, G. Gerig, “Parametric estimate of intensity inhomogeneities applied to MRI,” IEEE Trans, Med Imaging, vol. 19, no. 3, pp. 153-65, 2000.
[8] M. Ahmed, S. Yang, N. Mohamed, A. Fareg, T. Moritarty, “A modified fuzzy C-Means algorithm for bias field estimation and segmentation of MRI data,” IEEE Trans, Med Imaging, vol. 21 no. 3, pp. 193-9, 2002.
[9] C. Li, R. Huang, Z. Ding, C. Gatenby, D. Metaxas, J. Gore, “A variational level set approach to segmentation and bias correction of medical images with intensity inhomogeneity,” In Proc. Medical Image Computing and Computer Aided Intervention (MICCAI), vol. LNCS 5242, Part II, pp. 1083-91, 2008.
[10] B. Likar, M. Viergever, F. Pernus, “Retrospective   correction of MR intensity inhomogeneity by information minimization,” IEEE Trans, Med Imaging, vol. 20, no. 12, pp. 1398-410, 2001.
[11] U. Vovk, F. Pernus, B. Likar, “A review of methods for correction of intensity inhomogeneity in MRI,” IEEE Trans, Med Imaging, vol. 26, no. 3, pp. 405-21, 2007.
[12] B. Dawant, A. Zijdenbos, R. Margolin, “Correction of intensity variational in MR images for computer-aided tissue classification,” IEEE Trans, Med Imaging, vol. 12, no. 4, pp.770-81, 1993.
[13] Li. Chunming, H. Rui, D. Zhaohua, J.C. Gatenby, N. Dimitris, J.C. Gore, “A level set method for image segmentation in the presence of intensity inhomogeneity with application to MRI,” IEEE Trans, Image Processing, vol. 20, no. 7, pp. 1057-7149, 2011.  
[14] Li. Chunming, J.C. Gore, C. Davatzikos, “Multiplicative intrinsic optimization (MICO) for MRI bias field estimation and tissue segmentation,” Elsevier, Magnetic Resonance Imaging, vol. 32, pp. 913-923, 2014.
[15] K. Samasundaram, S.P. Gayathri, “Brain segmentation in magnetic resonance images using fast fourier transform.” IEEE Trans, Emerging Trends in Science, pp. 978-1-4673-5144-7, 2012.
[16] T. Chan, L. Vese, “Active contours without edges,” IEEE Trans, Image Processing, vol. 10, no. 2, pp. 266-277, 2001.
[17] C. Li, C. Kao, J.C. Gore, Z. Ding, “Minimization of region scalable fitting energy for image segmentation,” IEEE Trans, Image Processing, vol. 17, no. 10, pp. 1940-1949, 2008.
[18] R. Ranfard, “Region-based strategies for active contour models,” Int.J. Comput. Vis, vol. 13, no. 2, pp. 229-251, 1994.
[19] C. Samson, L. Blanc-Feraud, G. Aubert, and J. Zerubia, “A    variational model for image classification and restoration,” IEEE Trans, Pattern Anal. Mach. Intell, vol. 22, no. 5, pp. 460-472, 2000.
[20] A. Tsai, A. Yezzi, and A.S. Willsky, “Curve evolution implementation of the mumford-shah functional for image segmentation, Denoising, interpolation, and magnification,” IEEE Trans, Image Process, vol. 10, no. 8, pp. 1169-1186, 2001.
[21] L. Vese and T. Chan, “A multiphase level set framework for image segmentation using the mumford and shah model,” Int.J. Comput. Vis, vol. 50, no. 3, pp. 271-293, 2002.
[22] V. Caselles, R. Kimmel, and G. Sapiro, “Geodesic active contours,” Int. J. Comput. Vis, vol. 22, no. 1, pp. 61-79, 1997.
[23] S. Kichenassamy, A. Kumar, P. Olver, A. Tannenbaum and A. Yezzi, “Gradient flows and geometric active contour models,” In Proc. 5th Int. Conf. Comput, Vis, pp. 810-815, 1995.
[24] R. Kimmel, A. Amir, and A. Buckstein, “Finding shortest paths on surfaces using level set propagation,” IEEE Trans, Pattern Anal. Mach. Intell, vol. 17, no. 6, pp. 635-640, 1995.
[25] R. Malladi, J.A. Sethian, and B.C. Vemuri, “Shape modeling with front propagation: A level set approach,” IEEE Trans, Pattern Anal. Mach. Intell, vol. 17, no. 2, pp. 158-175, 1995.
[26] A. Vasilevskiy and K. Siddiqi, “Flux- maximization geometric flows,” IEEE Trans, Pattern Anal. Mach. Intell, vol. 24, no. 12, pp. 1565-1578, 2002.
[27] C. Li, C. Kao, J. C. Gore, Z. Ding, “Minimization of region-scalable fitting energy for image segmentation,” IEEE Trans. Image Process, vol. 17, no. 10, pp. 1940-1949, 2010.
[28] P. Kalavathi, “Brain tissue segmentation in MR brain images using multiple outs’s thresholding technique.” IEEE Computer Science & Education, pp. 978-1-4673-4463-0, 2010.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار