نوع مقاله : یادداشت کوتاه پژوهشی

نویسندگان

1 کارشناس ارشد مهندسی پزشکی، بیوالکتریک، دانشگاه صنعتی سهند

2 آزمایشگاه علوم اعصاب محاسباتی، گروه مهندسی پزشکی، دانشگاه صنعتی سهند. استادیار مهندسی پزشکی، بیوالکتریک، دانشگاه صنعتی سهند

10.22041/ijbme.2013.13091

چکیده

بخش بندی تصویر را به بخش های مجزا تقسیم میکند که هر کدام از این بخش ها دارای سطوح روشنایییکنواختی هستند. از بین روشهای موجود روش خوشه بندیفازی FCM (fuzzy c-means clustering) دارای کاربرد وسیعی در ناحیهبندی تصاویر پزشکی است. عدم ادغام ویژگیهای مکانی در FCM استاندارد، از معایب این روش در ناحیهبندی تصاویر تشدید مغناطیسی MRI مغز انسان است؛ در این مقاله از روشی جدید برای بخشبندی و حذف نویز تصاویر MR با اعمال فیلتر مکانی گوسی در تابع عضویت فازی استفاده شده است. فیلتر مکانی مذکور، اثرات نویز در مرز بافتها و زوایای تصویر را بصورت بهینه ای مدیریت میکند؛ علاوه براین پیکسلی که به لحاظ آناتومیکییک بافت مجزا است مانند تومور در مراحل اولیه‌ی رشد، شانس بیشتریبراییک خوشه شدن دارد. در پایان آزمایشات که بر روی پایگاه داده ISBR انجام شده است کیفیت روش پیشنهادی توسط توابع اعتبارسنجیمتداول مانند شاخص جاکارد و ضریب دایس مورد ارزیابی قرار گرفته است. از طرف دیگر در کاربردهای پزشکی به خصوص در شرایط اورژانسی، ضرورت سرعت عمل تمام عوامل پزشکی امری اجتناب ناپذیر است و الگوریتم ناحیه‌بندی از این قاعده مستثتی نیست، لذا برای دستیابی به این مهم توسط الگوریتمی مرکز ثقل اولیهی خوشهها ، مشخص میشود که زمان همگرایی تابع هزینه در FCM بهبود یافتهی مکانی گوسی، نسبت به  CM استاندارد تا حد قابل قبولی کاهش مییابد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Magnetic Resonsnce image segmentation by modified spatial FCMbased on Gaussian function

نویسندگان [English]

  • Abbas Biniaz 1
  • Ataollah Abbasi 2
  • Mousa Shamsi 2

1 M.Sc Student, Faculty of Biomedical Engineering, Bio Electrical Group,Sahand University

2 Assistant Professor, Faculty of Biomedical Engineering, Bio Electrical Group,Sahand University

چکیده [English]

Segmentation divides an image to some subdivisions where which of ones has similar intensity gray levels. Among clustering methods fuzzy c-means (FCM) clustering has been frequently used for segmentation of medical images. However, this algorithm doesn’t incorporate spatial neighborhood information in segmentation. This approach is very susceptible to nuisance factors. Therefore this paper proposes a Gaussian spatial FCM (gsFCM) to MR image segmentation. Proposed method has less sensitivity to noise specially in tissue boundaries, angles, and borders than spatial FCM (sFCM). Furthermore by the suggested algorithm a pixel which is a separate tissue from structurally point of view for example a tumor in primary stages of its appearance, has more chance to be a unique cluster. Applying quantitative assessments using Jaccard similarity index, Dice coefficient, and other validation functions on FCM,sFCM and gsFCM approaches show efficient performance of the proposed method. In this research the ISBR data bank is used for simmulations.Moreover in medical applications getting patient condition and information with fast methods is very important especially in emergency circumstances. Therefore all effective agents in patient health must be fast even medical algorithms such as clustering ones . Hence in this paper to decrease the time of convergence considerably and decline the number of iterations significantly, cluster centroids are initialized by an algorithm.

کلیدواژه‌ها [English]

  • component
  • Segmentation
  • MR brain image
  • FCM
  • spatial information filtering
  • initial cluster centriods
  • Gaussian membership function
[1]   K. Chuang, H. Tzeng, S. Chen, J. Wu, and T. Chen, "Fuzzy c-means clustering with spatial information for image segmentation," Computerized Medical Imaging and Graphics, vol. 30, pp. 9-15, 2006.
[2]   P. K. Sahoo, S. Soltani, and A. Wong, "A survey of thresholding techniques," Computer vision, graphics, and image processing, vol. 41, pp. 233- 260, 1988.
[3]   R. M. Haralick and L. G. Shapiro, "Image segmentation techniques," Computer vision, graphics, and image processing, vol. 29, pp. 100- 132, 1985.
[4]   I .I. T. MODEL, "Unsupervised Texture Segmentation Using Markov Random Field Models".
[5]   L. Lin, D. Garcia-Lorenzo, C. Li, T. Jiang, and C. Barillot, "Adaptive pixon represented segmentation (APRS) for 3D MR brain images based on mean shift and Markov random fields," Pattern Recognition Letters, vol. 32, pp. 1036- 1043, 2011.
[6]   W. Cai, S. Chen, and D. Zhang, "Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation," Pattern Recognition, vol. 40, pp. 825-8 ,2007,38.
[7]   W. Cai, S. Chen, and D. Zhang, "Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation," Pattern Recognition, vol. 40, pp. 825-838, 2007.
[8]   H. Van Lung and J.-M. Kim, "A generalized spatial fuzzy c-means algorithm for medical image segmentation," in Fuzzy Systems, 2009. FUZZIEEE 2009. IEEE International Conference on, 2009, pp. 409-414
[9]   R. Venkateswaran and S. Muthukumar, "Genetic Approach on Medical Image Segmentation by Generalized Spatial Fuzzy C-Means Algorithmǁ," in 2010 IEEE International Conference on Computational Intelligence and Computing Research, pp. 210-213.
[10]           K. Chuang, H. Tzeng, S. Chen, J. Wu, and T. Chen, "Fuzzy c-means clustering with spatial information for image segmentation," Computerized Medical Imaging and Graphics, vol. 30, pp. 9-15, 2006.
[11]           P. K. Sahoo, S. Soltani, and A. Wong, "A survey of thresholding techniques," Computer vision, graphics, and image processing, vol. 41, pp. 233- 260, 1988.
[12]           R. M. Haralick and L. G. Shapiro, "Image segmentation techniques," Computer vision, graphics, and image processing, vol. 29, pp. 100- 132, 1985.
[13]           I .I. T. MODEL, "Unsupervised Texture Segmentation Using Markov Random Field Models".
[14]           L. Lin, D. Garcia-Lorenzo, C. Li, T. Jiang, and C. Barillot, "Adaptive pixon represented segmentation (APRS) for 3D MR brain images based on mean shift and Markov random fields," Pattern Recognition Letters, vol. 32, pp. 1036- 1043, 2011.
[15]           W. Cai, S. Chen, and D. Zhang, "Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation," Pattern Recognition, vol. 40, pp. 825-8 ,2007,38.
[16]           W. Cai, S. Chen, and D. Zhang, "Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation," Pattern Recognition, vol. 40, pp. 825-838, 2007.
[17]           H. Van Lung and J.-M. Kim, "A generalized spatial fuzzy c-means algorithm for medical image segmentation," in Fuzzy Systems, 2009. FUZZIEEE 2009. IEEE International Conference on, 2009, pp. 409-414.
[18]           R. Venkateswaran and S. Muthukumar, "Genetic Approach on Medical Image Segmentation by Generalized Spatial Fuzzy C-Means Algorithmǁ," in 2010 IEEE International Conference on Computational Intelligence and Computing Research, pp. 210-213.
[19]           R. B. Dubey, M. Hanmandlu, S. K. Gupta, and S. K. Gupta, "The Brain MR Image Segmentation Techniquesand use of Diagnostic Packages," Academic Radiology, vol. 17, pp. 658-671, 2010.
[20]           Z.-X. Ji, Q.-S. Sun, and D.-S. Xia, "A modified possibilistic fuzzy c-means clustering algorithm for bias field estimation and segmentation of brain  MR image," Computerized Medical Imaging and Graphics, vol. 35, pp. 383-397, 2011.
[21]           D. L. Pham, "Spatial models for fuzzy clustering," Computer Vision and Image Understanding, vol. 84, pp. 285-297, 2001.
[22]           S. Ramathilagam, R. Pandiyarajan, A. Sathya, R. Devi, and S. R .Kannan, "Modified fuzzy c-means algorithm for segmentation of T1–T2-weighted brain MRI," Journal of Computational and Applied Mathematics, vol. 235, pp. 1578-1586, 2011.
[23]           Demirhan and İ. Güler, "Combining stationary wavelet transform and self-organizing maps for brain MR image segmentation," Engineering Applications of Artificial Intelligence, vol. 24, pp. 358-367, 2011.
[24]           P. Anbeek, K. L. Vincken, G. S. van Bochove, M. J. P. van Osch, and J. van der Grond, "Probabilistic segmentation of braintissue in MR imaging," NeuroImage, vol. 27, pp. 795-804, 2005.
[25]           M. Forouzanfar, N. Forghani, and M. Teshnehlab, "Parameter optimization of improved fuzzy cmeans clustering algorithm for brain MR image segmentation," Engineering Applications of Artificial Intelligence, vol. 23, pp. 160-168, 2010.