A comparative study on segmentation methods of micro calcification in mammogram

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    The primary indication of breast cancer is the presence of calcification clusters. It is challenging and lengthy process for radiologists to identify and classify micro calcifications as non-cancerous or cancerous. In this proposed work, a novel method for the detection of micro calcification clusters in mammograms is explained that consists of two main sections. First, mammogram preprocessing is done. Second, micro calcification are segmented out. In preprocessing noise and label are removed as well as contrast is enhanced. Then various segmentation methods are used for comparison of calcification region. Watershed segmentation, Marker controlled watershed segmentation (MCWS), Texture segmentation and Level set segmentation methods are applied to Digital Database for Screening Mammography (DDSM) database. Results show that the MCWS provides quite acceptable detection performance. The major advantage of this method is its capability to detect micro calcifications perfectly even in case of very dense mammograms. The performance of different methods is evaluated by comparing the obtained segmented image with expert radiologist data. The comparison study aptly shows that the micro calcifications can be exactly segment and can avoid over segmentation problem of existing method.

     

     


  • Keywords


    Micro Calcification; Mammogram; Marker Controlled Watershed Segmentations

  • References


      [1] H-C. Kung, D. L. Hoyert, J. Xu, and S. L. Murphy, 'Deaths: final data for 2005,' National Vital Statistics Report, vol. 56, no.10, pp. 1–121, April 24, 2008.

      [2] E.A.Sickles,'Breast calcifications: Mammographic evaluation,'Radiology, vol. 160, pp. 289–293, 1986.

      [3] 'USF digital mammography home page,' http: //marathon.csee.usf.ecu/Mammography/Database.html,(accessed May 18, 2009).

      [4] Y. Wu and K. Doi,'Computerized detection of clustered microcalcifications in digital mammograms: Applications of artificial neural networks,' Med. Phys., Vol. 19, No. 3, pp.213-217,1992.

      [5] D. H. Davies and D. R. Dance,'Automatic computer detection of clustered calcifications in digital mammograms', Phys. Med., Biol., Vol. 35, No. 8, pp. 1111–1118,1990.

      [6] H.R. Jin,'Extraction of microcalcifcations from mammograms using morphological filter with multiple structuring elements', System Comput. Jpn. Vol.24,No.11, pp.66–74,1993.

      [7] H. Cheng, Y. M. Lui, and R. I. Freimanis,'A novel approach to microcalcifications detection using fuzzy logic techniques', IEEE Trans. Med. Imag.. Vol. 17,No. 3, pp. 425-430,1998.

      [8] Bhattacharya, M. and Das, A,'Fuzzy logic based segmentation of microcalcification in breast using digital mammograms considering multiresolution',International Machine Vision and Image Processing Conference,Vol.36.No.121, pp. 98–105 ,2007.

      [9] Balafar, M.A., Ramli, A.R., Saripan, M.I., Mahmud, R., Mashohor, S.andBalafar, M, 'New multi-scale medical image segmentation based on fuzzy C-mean (FCM)',The 2008 IEEE Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, pp. 66–70,2008.

      [10] Deka B, Ghosh D,'Watershed segmentation for medical ultrasound images', IEEE Int Conf Syst Man Cybernet,Vol.35,No.54, pp.3186,2006.

      [11] H. Li, K. J. Liu, and S. B. Lo,'Fractal modeling and segmentation for the enhancement of microcalcifications in digital mammograms', ZEEE Trans. Med. hag., Vol. 16, No. 6.pp.356-360,1997.

      [12] D. Song, W. Qian, L.P. Clarke,' Digital mammography: hybrid M-channel wavelet transform for microcalcifcation segmentation', 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Amsterdam,Vol.20,No.13, pp. 1069–1070,1996.

      [13] H. Yoshida, W. Zhang, W. Cai, K. Doi, R.M. Nishikawa, M.L. Giger,,'Optimizing wavelet transform based on supervised learning for detection of microcalcifications in digital mammograms', Proceedings of the IEEE International Conference on Image Processing, Vol. 3, No.3, pp. 152–155,1995.

      [14] Hua LI, Elmoataz AL, Fadilia J, Ruana Su, 'An improved image segmentation approach based on level set and mathematical morphology.' France: Dept. of Electronics & Inf. Eng., Huazhong Univ. of Science & Tech.; Vol.25,No.19,pp.189-195,2003.

      [15] R.B. Dubeya, M. Hanmandlub, S.K. Gupta, 'A comparison of two methods for the segmentation of masses in the digital mammograms',Computerized medical imaging graphics ,pp 185-191, 2010.

      [16] B. Sahiner, H. Chan, N. Petrick, M. Helvie, and L. Hadjiiski, 'Improvement of mammographic mass characterization using spiculation measures and morphological features,'Med. Phys., Vol. 28, No. 7, pp. 1455–1465,2001.

      [17] Kim, J.K., Park, J.M., Song, K.S. and Park. W,'Adaptive Mammographic Image Enhancement Using First Derivative and Local Statistics', IEEE Transactions on Medical Imaging, Vol. 16, No. 5, pp. 495-502,.1997.

      [18] P. F. Stetson, F. G. Sommer, and A. Macovski, 'Lesion constrast enhancement in medical ultrasound imaging', IEEE Trans. Med. Imag.,Vol. 16, pp. 416–425,1997.

      [19] Anna N. Karahaliou, Ioannis S. Boniatis, Spyros G. Skiadopoulos, Filippos N. Sakellaropoulos, Nikolaos S. Arikidis, Eleni A. Likaki, George S. Panayiotakis, and Lena I. Costaridou,'Breast Cancer Diagnosis: Analyzing Texture of Tissue Surrounding Microcalcifications', IEEE Trans., Vol. 12, No. 6, pp. 725- 731,2008.


 

View

Download

Article ID: 16571
 
DOI: 10.14419/ijet.v7i2.25.16571




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.