Abstract
This paper describes part of content-based image retrieval (CBIR) system that has been developed for mammograms. Details are presented of methods implemented to derive measures of similarity based upon structural characteristics and distributions of density of the fibroglandular tissue, as well as the anatomical size and shape of the breast region as seen on the mammogram. Well-known features related to shape, size, and texture (statistics of the gray-level histogram, Haralick’s texture features, and moment-based features) were applied, as well as less-explored features based in the Radon domain and granulometric measures. The Kohonen self-organizing map (SOM) neural network was used to perform the retrieval operation. Performance evaluation was done using precision and recall curves obtained from comparison between the query and retrieved images. The proposed methodology was tested with 1,080 mammograms, including craniocaudal and mediolateral-oblique views. Precision rates obtained are in the range from 79% to 83% considering the total image set. Considering the first 50% of the retrieved mages, the precision rates are in the range from 78% to 83%; the rates are in the range from 79% to 86% considering the first 25% of the retrieved images. Results obtained indicate the potential of the implemented methodology to serve as a part of a CBIR system for mammography.
Similar content being viewed by others
References
Wolfe JN: Risk for breast cancer development determined by mammographic parenchymal pattern. Cancer 37:2486-2492, 1976
Boyd NF, Byng JW, Long RA, Fishell EK, Little LE, Miller AB, Lockwood GA, Tritchler DL, Yaffe MJ: Quantitative classification of mammographic densities and breast cancer risk: results from the Canadian National Breast Screening study. J Natl Cancer Inst 87:670-675, 1995
American College of Radiology—Breast Imaging Reporting and Data system, 3rd edition. Reston, VA: American College of Radiology, 1992
Zhou C, Chan H-P, Petrick N, Helvie MA, Goodsit MM, Sahiner B, Hadjiiski LM: Computerized image analysis: Estimation of breast density on mammograms. Med Phys 28(6):1056–1069, 2001
Doi K: Computer-aided diagnosis and its potential impact on diagnostic radiology. In: Doi K, MacMahon H, Giger ML, Hoffmann KR Eds. Computer-Aided Diagnosis in Medical imaging. Amsterdam, The Netherlands: Elsevier Science, 1999. pp 11–20
Rui Y, Huang TS, Ortega M, Mehrotra S: Relevance feedback: a power tool for interactive content-based image retrieval. IEEE Trans Circuits Syst Video Technol 8:644–655, 1998
Li Q, Li F, Shiraishi J, Katsuragawa S, Sone S, Doi K: Investigation of new psychophysical measures for evaluation of similar images on thoracic computed tomography for distinction between benign and malignant nodules. Med Phys 30(10):2584–2593, 2003
Azevedo-Marques PM, Honda MH, Rodrigues JAH, Santos RR, Traina AJM, Traina JR, Bueno JM: Recuperação de imagem baseada em conteúdo: uso de atributos de textura para caracterização de microcalcificações mamográficas. Radiol Bras 35(2):93–98, 2002
Alto H, Rangayyan RM, Desautels JEL: Content-based retrieval and analysis of mammographic masses. J Electron Imaging 14(2):Article 023016:1–17, 2005
Müller H, Michoux N, Bandond D, Geissbuhler A: A review of content-based image retrieval systems in medical applications-clinical benefits and future directions. Int J Med Informatics 73:1–23, 2004
El-Naqa I, Yang Y, Galatsanos NP, Nishikawa RM, Wernick MN: A similarity learning approach to content-based image retrieval application to digital mammography. IEEE Trans Med Imag 23(10):1233–1244, 2004
Muramatsu C, Li Q, Suzuki K, Schmidt RA, Shiraishi J, Newstead GM, Doi K: Investigation of psychophysical measure for evaluation of similar images for mammographic masses: Preliminary results. Med Phys 32:2295–2304, 2005
Tao EY, Sklansky J: Analysis of mammograms aided by database of images of calcifications and textures. Proc SPIE 2710:988–995, 1996
Ornes CJ, Valentino DJ, Yoon H-J, Eisenman JI, Sklansky J: Search engine for remote database-aided interpretation of digitized mammograms. Proc SPIE 4323:132–137, 2001
El-Naqa I, Yang Y, Galatsanos NP, Wernick MN: Content-based image retrieval for digital mammography. Proceedings of the International Conference on Image Processing, Rochester, New York, USA (3):141–144, 2002
Nakagawa T, Hara T, Fujita H, Iwase T, Endo T: Image retrieval system of mammographic masses by using local pattern technique. Proceedings of the International Workshop on Digital Mammography—IWDM2002. Bremen, Germany, 2002, pp 562–565
Nakagawa T, Hara T, Fujita H, Iwase T, Endo T: Development of a computer-aided sketch system for mammograms. Proceedings of the International Workshop on Digital Mammography—IWDM2002. Bremen, Germany, 2002, pp 581–583
Kohonen T: The self-organizing map. Proc IEEE 78(9):1464–1480, 1990
Laaksonen J, Koskela M, Laakso S, Oja E: PicSOM—content-based image retrieval with self-organizing maps. Pattern Recogn Lett 21(13–14):1199–1207, 2000
Perona P, Malik J: Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12(7):629–639, 1990
Kinoshita SK, Pereira RR, Honda MO, Rodrigues JAH, Azevedo-Marques PM: Segmentation of the breast region from noisy mammograms and automatically locating the nipple and pectoral muscle region. Proceedings of the International Workshop on Digital Mammography—IWDM2004, Durham, NC, 2004, pp 629–634
Sahoo PK, Soltani S, Wong AKC, Chen YC: A survey of thresholding techniques. Comput Vis Graph Image Process 41:233–260, 1988
Ridler T, Carvard S: Picture thresholding using an iterative selection method. IEEE Trans Syst Man Cybern 8:630–632, 1978
Reddi SS, Rudin SF, Keshavan HR: An optimal multiple threshold scheme for image segmentation. IEEE Trans Syst Man Cybern 14:661–665, 1984
Canny J: A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698, 1986
Rangayyan RM, Rolston WA: Directional image analysis with the Hough and Radon transforms. J Indian Inst Sci 78:3–16, 1998
Dougherty ER, Newell JT, Pelz JB: Morphological texture-maximum-likelihood pixel classification based on local granulometric moments. Pattern Recogn 25(10):1181–1198, 1992
Haralick RM, Shanmugan K, Dinstein I: Texture features for image classification. IEEE Trans Syst Man Cybern 3:610–621, 1973
Hu MK: Visual pattern recognition by moment invariants. IRE Trans Inf Theory 8(2):170–187, 1962
Acknowledgment
We thank the radiologists and faculty members of the Clinical Hospital of the Faculty of Medicine, University of São Paulo, Ribeirão Preto, SP, Brazil, for providing the mammograms and the related reports used in this work. We thank the State of São Paulo Research Foundation (FAPESP), the National Council for Scientific and Technological Development (CNPq), and the Foundation to Aid Teaching, Research, and Patient Care of the Clinical Hospital of Ribeirão Preto (FAEPA/HCRP) for financial support. This work was also supported by a Catalyst grant from Research Services, University of Calgary.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kinoshita, S.K., de Azevedo-Marques, P.M., Pereira, R.R. et al. Content-based Retrieval of Mammograms Using Visual Features Related to Breast Density Patterns. J Digit Imaging 20, 172–190 (2007). https://doi.org/10.1007/s10278-007-9004-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-007-9004-0