Gabor filters and phase portraits for the detection of architectural distortion in mammograms

  • Rangaraj M. Rangayyan
  • Fábio J. Ayres
Original Article


Architectural distortion is a subtle abnormality in mammograms, and a source of overlooking errors by radiologists. Computer-aided diagnosis (CAD) techniques can improve the performance of radiologists in detecting masses and calcifications; however, most CAD systems have not been designed to detect architectural distortion. We present a new method to detect and localise architectural distortion by analysing the oriented texture in mammograms. A bank of Gabor filters is used to obtain the orientation field of the given mammogram. The curvilinear structures (CLS) of interest (spicules and fibrous tissue) are separated from confounding structures (pectoral muscle edge, parenchymal tissue edges, breast boundary, and noise). The selected core CLS pixels and the orientation field are filtered and downsampled, to reduce noise and also to reduce the computational effort required by the subsequent methods. The downsampled orientation field is analysed to produce three phase portrait maps: node, saddle, and spiral. The node map is further analysed in order to detect the sites of architectural distortion. The method was tested with 19 mammograms containing architectural distortion. In a preliminary experiment, a sensitivity of 84% was obtained at 7.8 false positives per image.


Architectural distortion Phase portraits Oriented texture Gabor filters Mammography Breast cancer Computer-aided diagnosis 



This work was supported by the Natural Sciences and Engineering Research Council of Canada. We thank Dr. J. E. L. Desautels, Screen Test Alberta, for his assistance in this project.


  1. 1.
    American College of Radiology (ACR) (1998) Illustrated breast imaging reporting and data system (BI-RADS), 3rd edn. American College of Radiology, RestonGoogle Scholar
  2. 2.
    Ayres FJ, Rangayyan RM (2004) Detection of architectural distortion in mammograms using phase portraits. In: Fitzpatrick JM, Sonka M (eds) Proceedings of SPIE medical imaging 2004: image processing, vol 5370. San Diego, pp 587–597Google Scholar
  3. 3.
    Ayres FJ, Rangayyan RM (2005a) Characterization of architectural distortion in mammograms. IEEE Eng Med Biol Mag 24(1):59–67CrossRefGoogle Scholar
  4. 4.
    Ayres FJ, Rangayyan RM (2005b) Detection of architectural distortion in mammograms via analysis of phase portraits and curvilinear structures. In: Hozman J, Kneppo P (eds) Proceedings of EMBEC’05: 3rd European medical and biological engineering conference, vol 11. Prague, Czech Republic, pp 1768–1773Google Scholar
  5. 5.
    Ayres FJ, Rangayyan RM (2005c) Performance analysis of oriented feature detectors. In: Proceedings of SIBGRAPI 2005: XVIII Brazilian symposium on computer graphics and image processing. IEEE Computer Society Press, Natal, pp 147–154Google Scholar
  6. 6.
    Baker JA, Rosen EL, Lo JY, Gimenez EI, Walsh R, Soo MS (2003) Computer-aided detection (CAD) in screening mammography: Sensitivity of commercial CAD systems for detecting architectural distortion. Am J Roentgenol 181:1083–1088Google Scholar
  7. 7.
    Bird RE, Wallace TW, Yankaskas BC (1992) Analysis of cancers missed at screening mammography. Radiology 184:613–617Google Scholar
  8. 8.
    Broeders MJM, Onland-Moret NC, Rijken HJTM, Hendriks JHCL, Verbeek ALM, Holland R (1993) Use of previous screening mammograms to identify features indicating cases that would have a possible gain in prognosis following earlier detection. Eur J Cancer 39:1770–1775CrossRefGoogle Scholar
  9. 9.
    Burrell HC, Sibbering DM, Wilson ARM, Pinder SE, Evans AJ, Yeoman LJ, Elston CW, Ellis IO, Blamey RW, Robertson JFR (1996) Screening interval breast cancers: Mammographic features and prognostic factors. Radiology 199:811–817Google Scholar
  10. 10.
    Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698CrossRefGoogle Scholar
  11. 11.
    Cerneaz N, Brady M (1994) Enriching digital mammogram image analysis with a description of the curvi-linear structures. In: Gale AG, Astley SM, Dance DR, Cairns AY (eds) Digital mammography: proceedings of the 2nd international workshop on digital mammography. Elsevier, York, pp 297–306Google Scholar
  12. 12.
    Dougherty ER (1992) An introduction to morphological image processing. SPIE, BellinghamGoogle Scholar
  13. 13.
    Ferrari RJ, Rangayyan RM, Desautels JEL, Frère AF (2001) Analysis of asymmetry in mammograms via directional filtering with Gabor wavelets. IEEE Trans Med Imaging 20(9):953–963CrossRefGoogle Scholar
  14. 14.
    Ferrari RJ, Rangayyan RM, Borges RA, Frère AF (2004a) Segmentation of the fibro-glandular disc in mammograms using Gaussian mixture modeling. Med Biol Eng Comput 42:378–387CrossRefGoogle Scholar
  15. 15.
    Ferrari RJ, Rangayyan RM, Desautels JEL, Borges RA, Frère AF (2004b) Identification of the breast boundary in mammograms using active contour models. Med Biol Eng Comput 42:201–208CrossRefGoogle Scholar
  16. 16.
    Gershenfeld N (1999) The nature of mathematical modeling. Cambridge University Press, CambridgezbMATHGoogle Scholar
  17. 17.
    Homer MJ (1997) Mammographic interpretation: a practical approach, 2nd edn. McGraw-Hill, New YorkGoogle Scholar
  18. 18.
    Ichikawa T, Matsubara T, Hara T, Fujita H, Endo T, Iwase T (2004) Automated detection method for architectural distortion areas on mammograms based on morphological processing and surface analysis. In: Fitzpatrick JM, Sonka M (eds) Proceedings of SPIE medical imaging 2004: image processing, SPIE, San Diego, pp 920–925Google Scholar
  19. 19.
    Jamal A, Clegg LX, Ward E, Ries LAG, Wu X, Jamison PM, Wingo PA, Howe HL, Anderson RN, Edwards BK (2004) Annual report to the nation on the status of cancer, 1975–2001, with a special feature regarding survival. Cancer 101(1):3–27CrossRefGoogle Scholar
  20. 20.
    Karssemeijer N, te Brake GM (1996) Detection of stellate distortions in mammograms. IEEE Trans Med Imaging 15(5):611–619CrossRefGoogle Scholar
  21. 21.
    Kass M, Witkin A (1987) Analyzing oriented patterns. Comput Vis Graph Image Process 37:362–385CrossRefGoogle Scholar
  22. 22.
    Kegelmeyer WP Jr (1994) Evaluation of stellate lesion detection in a standard mammogram data set. In: Bowyer KW, Astley S (eds) State of the art in digital mammographic image analysis. World Scientific, Singapore, pp 262–279Google Scholar
  23. 23.
    Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220(4598):671–680MathSciNetCrossRefGoogle Scholar
  24. 24.
    Liu S, Babbs CF, Delp EJ (2001) Multiresolution detection of spiculated lesions in digital mammograms. IEEE Trans Image Process 10(6):874–884zbMATHCrossRefGoogle Scholar
  25. 25.
    Manjunath BS, Ma WY (1996) Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Mach Intell 18(8):837–842CrossRefGoogle Scholar
  26. 26.
    Matsubara T, Fukuoka D, Yagi N, Hara T, Fujita H, Inenaga Y, Kasai S, Kano A, Endo T, Iwase T (2005) Detection method for architectural distortion based on analysis of structure of mammary gland on mammograms. In: Proceedings of the 19th international congress and exhibition on computer assisted radiology and surgery (CARS 2005). Elsevier, Berlin, pp 1036–1040Google Scholar
  27. 27.
    Metz CE (1986) ROC methodology in radiologic imaging. Invest Radiol 21:720–733CrossRefGoogle Scholar
  28. 28.
    Mudigonda NR, Rangayyan RM (2001) Texture flow-field analysis for the detection of architectural distortion in mammograms. In: Ramakrishnan AG (ed) Proceedings of biovision, Bangalore, pp 76–81Google Scholar
  29. 29.
    Mudigonda NR, Rangayyan RM, Desautels JEL (2001) Detection of breast masses in mammograms by density slicing and texture flow-field analysis. IEEE Trans Med Imaging 20(12):1215–1227CrossRefGoogle Scholar
  30. 30.
    National Cancer Institute of Canada (2005) Canadian cancer statistics 2005. Toronto, Canada, available at, accessed on Oct 27, 2005.
  31. 31.
    Nguyen HT, Hung WT, Thornton BS, Lee W, Rickard M, Berry MW (2001) Detection of stellates and masses in digitised mammograms. In: Proceedings of the 23rd annual international conference of the IEEE engineering in medicine and biology society (CD-ROM), Istanbul, Turkey, pp 2709–2711Google Scholar
  32. 32.
    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66MathSciNetCrossRefGoogle Scholar
  33. 33.
    Qian W, Li L, Clarke LP, Mao F, Clark RA (1998) Adaptive CAD modules for mass detection in digital mammography. In: Chang HK, Zhang YT (eds) Proceedings of the 20th annual international conference of the IEEE engineering in medicine and biology society, vol 2. Hong Kong, pp 1013–1016Google Scholar
  34. 34.
    Rao AR (1990) A taxonomy for texture description and identification. Springer, Berlin Heidelberg New YorkzbMATHGoogle Scholar
  35. 35.
    Rao AR, Jain RC (1992) Computerized flow field analysis: oriented texture fields. IEEE Trans Pattern Anal Mach Intell 14(7):693–709CrossRefGoogle Scholar
  36. 36.
    Rao AR, Schunck BG (1991) Computing oriented texture fields. Comput Vis Graph Image Process 53(2):157–185Google Scholar
  37. 37.
    Sampat MP, Whitman GJ, Markey MK, Bovik AC (2005) Evidence based detection of spiculated masses and architectural distortion. In: Fitzpatrick JM, Reinhardt JM (eds) Proceedings of SPIE medical imaging 2005: image processing, vol 5747, San Diego, pp 26–37Google Scholar
  38. 38.
    Sickles EA (1986) Mammographic features of 300 consecutive nonpalpable breast cancers. Am J Roentgenol 146:661–663Google Scholar
  39. 39.
    Sonka M, Hlavac V, Boyle R (1993) Image processing, analysis and machine vision, 1st edn. Chapman & Hall, LondonGoogle Scholar
  40. 40.
    Suckling J, Parker J, Dance DR, Astley S, Hutt I, Boggis CRM, Ricketts I, Stamakis E, Cerneaz N, Kok SL, Taylor P, Betal D, Savage J (1994) The mammographic image analysis society digital mammogram database. In: Gale AG, Astley SM, Dance DD, Cairns AY (eds) Digital mammography: proceedings of the 2nd international workshop on digital mammography, Elsevier, York, pp 375–378Google Scholar
  41. 41.
    Wylie CR, Barrett LC (1995) Advanced engineering mathematics, 6th edn. McGraw-Hill, New YorkzbMATHGoogle Scholar
  42. 42.
    Zwiggelaar R, Parr TC, Hutt IW, Taylor CJ, Astley SM, Boggis CRM (1999) Model-based detection of spiculated lesions in mammograms. Med Image Anal 3(1):39–63CrossRefGoogle Scholar
  43. 43.
    Zwiggelaar R, Astley SM, Boggis CRM, Taylor CJ (2004) Linear structures in mammographic images: detection and classification. IEEE Trans Med Imaging 23(9):1077–1086CrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2006

Authors and Affiliations

  1. 1.Department of Electrical and Computer Engineering, Schulich School of EngineeringUniversity of CalgaryCalgaryCanada
  2. 2.Department of RadiologyUniversity of CalgaryCalgaryCanada

Personalised recommendations