Author : Hakeem Aejaz Aslam 1
Date of Publication :7th March 2017
Abstract: In this paper, the use of different enhancement techniques to increase the contrast of the mammogram is presented. By far, the best method to come up with is the Laplacian pyramid method. In this method, the original image is convolved with a Gaussian kernel which is a low pass filtering operation with the band limit reduced correspondingly by one octave with each level. The Laplacian Pyramid differentiates smoothed brightness values and produces a set of band pass filtered copies of the original image. The Laplacian pyramid with level 5 is presented in this paper. Then the reconstructed images are finally brought back the original image with increased contrast by subtracting the images of each level of the pyramid with the reconstructed images. It is shown that the visibility of micro calcification clusters and anatomic details is considerably improved in the processed images. The code of this algorithm is generated using MATLAB 7.5 software.
Reference :
-
[1] Breast Cancer organization, "",Accessed September 17, 2011.
[2] PajakDawid, Martin Cadik, et al, “Contrast Prescription for Multiscale ImageEditing,” The Visual Computer, 2010, Vol. 26, No. 6-8, 739-748.
[3] Bick U., F. Diekmann, "Digital Mammography Book," Springer-Verlag BerlinHeidelberg, 2010.
[4] Loza A., david Bull, AlinAchim, "Automatic Contrast Enhancement of Low-Light Images Based on Local Statistics of Wavelet Coefficients," IEEE 17thInternational Conference on Image Processing, 2010, 3553-3556.
[5] Gonzalez R.C. and Richard E. Woods, “Digital Image Processing,” Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA, 2008.
[6] Mainardi L., K. Passera, A. Lucesoli, D. Vergnaghi, G. Trecate, E. Setti, R.Musumeci, and S. Cerutti, “A nonrigid registration of breast MR images usingcomplex-valued wavelet transform,” Journal of Digital Imaging, 2007,PMCID: PMC3043828, 27-36.
[7] Paquin D., "Multiscale Method for Image Registration,"Doctor of PhilosophyDissertation of the Department of Mathematics at Stanford University, 2007.
[8] Singh Sameer, Member, IEEE, and KeirBovis, "An Evaluation of ContrastEnhancement Techniques for Mammographic Breast Masses," IEEETransactions on Information Technology in Biomedicine, 2005, Vol. 9, No. 1,109-119.
[9] Mahesh Mahadevappa, "Digital Mammography: An Overview,"RadioGraphics, RSNA 2004, Vol 24, No. 6, 1747-1760. [10] Pisano et al, "Digital Mammography," Lippincott Williams and Wilkins,Philadelphia, PA, USA, 2004.
[11] Heinlein Peter, Johann Drexl, and Wilfried Schneider, “Integrated Wavelets forEnhancement of Microcalcifications in Digital Mammography,” IEEE Transactions on Medical Imaging, 2003, Vol. 22, No. 3, 402-413.
[12] Chen S. D., and A. R. Ramli, “Contrast enhancement using recursivemeanseparate histogram equalization for scalable brightness preservation,”IEEE Trans. Consumer Electronics, November 2003, Vol. 49, No. 4, 1301-1309.
[13] Chen Soong-Der, and A. R. Ramli, “Minimum mean brightness errorbihistogram equalization in contrast enhancement,” IEEE Transactions onConsumer Electronics, 2003, Vol. 49, No. 4, 1310-1319.
[14] Cheng H. D., HuijuanXu, “A novel fuzzy logic approach to mammogramcontrast enhancement,” Information Sciences, 2002, Vol. 148, 167-184.
[15] Dippel Sabine, Martin Stahl, Rafael Wiemker, Thomas Blaffert, "Multiscale ContrastEnhancement for Radiographies: Laplacian Pyramid versus FastWavelet Transform", IEEE Transaction on Medical Imaging, Vol. 21, No. 4,2002, 343-353.