Detection Of The Breast Contour In Mammograms By Using Active Contour Models
We present a method for identification of the breast boundary in mammograms that is intended to be used in the preprocessing stage of a system for computer-aided diagnosis (CAD) of breast cancer and also in the reduction of image file size in Picture Archiving and Communication System (PACS) applications. The method starts by modifying the contrast of the original image. A binarization procedure is then applied to the image, and the chaincode algorithm is used to find an approximate breast contour. Finally, identification of the true breast boundary is performed by using the approximate contour as the input to an active contour model algorithm specially tailored for this purpose. After demarcating the breast boundary, all artifacts outside the breast region are eliminated. The method was applied to 84 medio-lateral oblique mammograms from the Mini-MIAS (Mammographic Image Analysis Society, London, UK) database. Evaluation of the breast boundary detected was performed based upon the percentage of false-positive (FP) and false-negative (FN) pixels determined by a quantitative comparison between the contours identified by a radiologist and by the proposed method. The average FP and FN rates are 0.41 and 0.58%, respectively. According to two radiologists who evaluated the results, the segmentation results were considered acceptable for CAD purposes.
KeywordsOriginal Image Active Contour Active Contour Model Initial Contour Digital Mammogram
Unable to display preview. Download preview PDF.
- 2.Bick U, Giger ML, Schmidt RA, Nishikawa RM, Doi K. 1996. Density correction of peripheral breast tissue on digital mammograms. RadioGraphics 16(6):1403-1411.Google Scholar
- 3.Byng JW, Critten JP, Yaffe MJ. 1997. Thickness-equalization processing for mammographic images. Radiology 203(2):564-568.Google Scholar
- 9.Masek M, AttikiouzelY, deSilva CJS. 2000. Combining data from different algorithms to segment the skin-air interface in mammograms. In Proceedings of the 22nd annual EMBS international conference, Vol. 2, pp. 1195-1198. Washington, DC: IEEE.Google Scholar
- 10.Ferrari RJ, Rangayyan RM, Desautels JEL, Fr ère AF. 2000. Segmentation of mammograms: identification of the skin-air boundary, pectoral muscle, and fibro-glandular disc. In Proceedings of the 5th international workshop on digital Mammography, pp. 573-579. Ed MJYaffe. Madison, WI: Medical Physics Publishing.Google Scholar
- 12.Gonzalez RC, Woods RE. 1992. Digital image processing. Reading, MA:: Addison-Wesley.Google Scholar
- 13.Suckling J, Parker J, Dance DR, Astley S, Hutt I, Boggis CRM, Ricketts I, Stamatakis E, Cerneaz N, Kok SL, Taylor P, Betal D, Savage J. 1994. The mammographic image analysis society digital mammogram database. In Proceedings of the 2nd international workshop on digital mammogra-phy, pp. 375-378. Ed AG Gale, SM Astley, DR Dance, AY Cairns. Excerpta Medica International Congress Series, Vol. 1069. Amsterdam: Elsevier.Google Scholar
- 15.Mackiewich B. 1995. Intracranial boundary detection and radio frequency correction in mag-netic resonance images. Master’s thesis, School of Computing Science, Simon Fraser University, Burnaby, BC, Canada.Google Scholar
- 18.Mattis P, Kimball S. 2005. GIMP-GNU image manipulation program. http://www.gimp.org.