{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T13:36:53Z","timestamp":1770557813867,"version":"3.49.0"},"reference-count":51,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2009,12,1]],"date-time":"2009-12-01T00:00:00Z","timestamp":1259625600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Techniques in image similarity can be used to improve the classification of breast cancer images. Breast cancer images in the mammogram modality have an abundance of non-cancerous structures that are similar to cancer, which make classification of images as containing cancer especially difficult to work with. Only the cancerous part of the image is relevant, so the techniques must learn to recognize cancer in noisy mammograms and extract features from that cancer to appropriately classify images. There are also many types or classes of cancer with different characteristics over which the system must work. Mammograms come in sets of four, two images of each breast, which enables comparison of the left and right breast images to help determine relevant features and remove irrelevant features. In this work, image feature clustering is done to reduce the noise and the feature space, and the results are used in a distance function that uses a learned threshold in order to produce a classification. The threshold parameter of the distance function is learned simultaneously with the underlying clustering and then integrated to produce an agglomeration that is relevant to the images. This technique can diagnose breast cancer more accurately than commercial systems and other published results.<\/jats:p>","DOI":"10.3390\/a2041503","type":"journal-article","created":{"date-parts":[[2009,12,2]],"date-time":"2009-12-02T03:06:01Z","timestamp":1259723161000},"page":"1503-1525","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Image Similarity to Improve the Classification of Breast Cancer Images"],"prefix":"10.3390","volume":"2","author":[{"given":"Dave","family":"Tahmoush","sequence":"first","affiliation":[{"name":"US Army Research Laboratory, 2800 Powder Mill Rd, Adelphi, MD 20783, USA"}]}],"member":"1968","published-online":{"date-parts":[[2009,12,1]]},"reference":[{"key":"ref_1","unstructured":"American Cancer Society (1999). Breast Cancer Facts and Figures 1999\u20132000, American Cancer Society."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1148\/radiology.215.2.r00ma15554","article-title":"Potential contribution of computer-aided detection to the sensitivity of screening mammography","volume":"215","author":"Linda","year":"2000","journal-title":"Radiology"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1148\/radiol.2203001282","article-title":"Screening mammography with computer-aided detection: Prospective study of 12,860 patients in a community breast center","volume":"220","author":"Freer","year":"2001","journal-title":"Radiology"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1093\/jnci\/djh067","article-title":"Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system","volume":"96","author":"Gur","year":"2004","journal-title":"J. Natl. Cancer Inst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1148\/radiol.2372041362","article-title":"Computer-aided detection in the United Kingdom national breast screening programme: prospective study","volume":"237","author":"Khoo","year":"2005","journal-title":"Radiology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.2214\/AJR.05.1582","article-title":"Prospective assessment of computer-aided detection in interpretation of screening mammograms","volume":"187","author":"Ko","year":"2006","journal-title":"Am. J. Roentgenol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1148\/radiol.2332040277","article-title":"Computer-aided detection performance in mammographic examination of masses: assessment","volume":"233","author":"Gur","year":"2004","journal-title":"Radiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3135","DOI":"10.1118\/1.2237476","article-title":"Multiviewbased computer-aided detection scheme for breast masses","volume":"33","author":"Zheng","year":"2006","journal-title":"Med. Phys."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1118\/1.2168063","article-title":"Computer-aided detection in its present form is not an effective aid for screening mammography","volume":"33","author":"Nishikawa","year":"2006","journal-title":"Med. Phys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1056\/NEJMoa066099","article-title":"Influence of computer-aided detection on performance of screening mammography","volume":"356","author":"Fenton","year":"2007","journal-title":"New England J. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2123","DOI":"10.1118\/1.1589494","article-title":"Computer-assisted detection of mammographic masses: a template matching scheme based on mutual information","volume":"30","author":"Tourassi","year":"2003","journal-title":"Med. Phys."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Astley, S.M., Brady, M., Rose, C., and Zwiggelaar, R. (2006). Digital Mammography, Springer.","DOI":"10.1007\/11783237"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1109\/TMI.2004.834601","article-title":"A similarity learning approach to content-based image retrieval: application to digital mammography","volume":"23","author":"Yang","year":"2004","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1117\/12.594929","article-title":"A general framework for content-based medical image retrieval with its application to mammograms","volume":"5748","author":"Wei","year":"2005","journal-title":"Proc. SPIE"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"023016","DOI":"10.1117\/1.1902996","article-title":"Content-based retrieval and analysis of mammographic masses","volume":"14","author":"Alto","year":"2005","journal-title":"J. Electron. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"65141Z","DOI":"10.1117\/12.711528","article-title":"A preliminary study of content-based mammographic masses retrieval","volume":"6514","author":"Tao","year":"2007","journal-title":"Proc. SPIE"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1007\/s10278-007-9004-0","article-title":"Content-based retrieval of mammograms using visual features related to breast density patterns","volume":"20","author":"Kinoshita","year":"2007","journal-title":"J. Digit. Imaging"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1016\/j.acra.2007.04.012","article-title":"Interactive computer aided diagnosis of breast masses: computerized selection of visually similar image sets from a reference library","volume":"14","author":"Zheng","year":"2007","journal-title":"Acad. Radiol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1088\/0031-9155\/53\/4\/005","article-title":"Decision optimization of case-based computer-aided decision systems using genetic algorithm with application to mammography","volume":"53","author":"Mazurowski","year":"2008","journal-title":"Phys. Med. Biol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Rosa, N.A., Felipe, J.C., Traina, A.J., Rangayyan, R.M., and Azevedo-Marques, P.M. (2008, January August). Using relevance feedback to reduce the semantic gap in content-based image retrieval of mammographic masses. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vancouver, BC, USA.","DOI":"10.1109\/IEMBS.2008.4649176"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.acra.2008.08.012","article-title":"Improving performance of computer-aided detection scheme by combining results from two machine learning classifiers","volume":"16","author":"Park","year":"2009","journal-title":"Acad. Radiol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1117\/12.467222","article-title":"Intelligent CAD workstation for breast imaging using similarity to known lesions and multiple visual prompt aides","volume":"4684","author":"Giger","year":"2002","journal-title":"Proc. SPIE"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Tahmoush, D., and Samet, H. (,  2007). Image differencing approaches to medical image classification. Proceedings of the 36th Applied Imagery Pattern Recognition Workshop, Washington, DC, USA.","DOI":"10.1109\/AIPR.2007.9"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"65141Q","DOI":"10.1117\/12.708327","article-title":"An improved asymmetry measure to detect breast cancer","volume":"6514","author":"Tahmoush","year":"2007","journal-title":"Proc. SPIE"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"61441S","DOI":"10.1117\/12.652643","article-title":"Using image similarity and asymmetry to detect breast cancer","volume":"6144","author":"Tahmoush","year":"2006","journal-title":"Proc. SPIE"},{"key":"ref_26","first-page":"7260","article-title":"Augmenting medical image diagnosis through image similarity","volume":"7260","author":"Tahmoush","year":"2009","journal-title":"Proc. SPIE"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1109\/42.952732","article-title":"Analysis of asymmetry in mammograms via directional filtering with Gabor wavelets","volume":"20","author":"Ferrari","year":"2001","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Astley, S., Mistry, T., Boggis, C.R.M., and Hillier, V.F. (2002, January June). Should we use humans or a machine to pre-screen mammograms?. Proceedings of the Sixth International Workshop on Digital Mammography, Bremen, Germany.","DOI":"10.1007\/978-3-642-59327-7_112"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1016\/j.crad.2003.11.017","article-title":"Computer-aided detection in mammography","volume":"59","author":"Astley","year":"2004","journal-title":"Clin. Radiol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/BF00962238","article-title":"Efficient and effective querying by image content","volume":"3","author":"Faloutsos","year":"1994","journal-title":"J. Intell. Inf. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Goldberger, J., Gordon, S., and Greenspan, H. (2003, January October). An efficient image similarity measure based on approximations of kl-divergence between two gaussian mixtures. Proceedings of the Ninth IEEE International Conference on Computer Vision, Nice, France.","DOI":"10.1109\/ICCV.2003.1238387"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1145\/201040.201041","article-title":"Design and evaluation of algorithms for image retrieval by spatial similarity","volume":"13","author":"Gudivada","year":"1995","journal-title":"ACM Trans. Inf. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Soffer, A., and Samet, H. (,  1996). Pictorial queries by image similarity. Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria.","DOI":"10.1109\/ICPR.1996.546805"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1148\/radiology.163.2.3550885","article-title":"Icon: a computer-based approach to differential diagnosis in radiology","volume":"163","author":"Swett","year":"1987","journal-title":"Radiology"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1142\/S0218001497000627","article-title":"Automatic MRI database exploration and applications","volume":"11","author":"Guimond","year":"1997","journal-title":"Pattern Recognition Artif. Intell."},{"key":"ref_36","unstructured":"Gondra, I., and Heisterkamp, D.R. (2,, January June). Learning in region-based image retrieval with generalized support vector machines. Proceedings of the Computer Vision and Pattern Recognition, Washington, DC, USA."},{"key":"ref_37","unstructured":"Miller, P., and Astley, S. (5,, January January). Detection of breast asymmetry using anatomical features. Proceedings of the International Society for Optical Engineering Conference on Biomedical Image Processing and Biomedical Visualization, San Jose, CA, USA."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wirth, M.A., Choi, C., and Jennings, A. (1999, January July). A nonrigid-body approach to matching mammograms. Proceedings of the 7th International Conference on Image Processing and its Applications, San Jose, CA, USA.","DOI":"10.1049\/cp:19990369"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1118\/1.596610","article-title":"Computerized detection of masses in digital mammograms: analysis of bilateral subtraction images","volume":"18","author":"Yin","year":"1991","journal-title":"Med. Phys."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1109\/83.624955","article-title":"Establishing the correspondence between control points in pairs of Mammographic images","volume":"6","author":"Vujovic","year":"1997","journal-title":"IEEE Trans. Image Process."},{"key":"ref_41","unstructured":"Sallam, M., and Bowyer, K.W. (1996). Digital Mammography, Elsevier."},{"key":"ref_42","unstructured":"Yao, J., and Taylor, R. (2003, January October). Assessing accuracy factors in deformable 2D\/3D medical image registration using a statistical pelvis model. Proceedings of the Ninth IEEE International Conference on Computer Vision, Nice, France."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1117\/12.467198","article-title":"Nonrigid mammogram registration using mutual information","volume":"4684","author":"Wirth","year":"2002","journal-title":"Proc. SPIE"},{"key":"ref_44","unstructured":"Heath, M.D., and Bowyer, K.W. (2000). Digital Mammography, Medical Physics Publishing."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1148\/radiology.213.3.r99dc20889","article-title":"Benign versus malignant solid breast masses: US differentiation","volume":"213","author":"Rahbar","year":"1999","journal-title":"Radiology"},{"key":"ref_46","unstructured":"Kalman, B.L., Kwasny, S.C., and Reinus, W.R. (1998). Diagnostic screening of digital mammograms using wavelets and neural networks to extract structure, Washington University. Technical Report No. 98-20."},{"key":"ref_47","first-page":"874","article-title":"Multiresolution detection of spiculated lesions in digital mammograms","volume":"6","author":"Lui","year":"2001","journal-title":"IEEE Trans. Image Process."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Campanini, R., Bazzani, A., Bevilacqua, A., and Bollini, D. (2002, January June). A novel approach to mass detection in digital mammography based on support vector machines. Proceedings of the 6th International Workshop on Digital Mammography, Bremen, Germany.","DOI":"10.1007\/978-3-642-59327-7_93"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1093\/bioinformatics\/btf867","article-title":"Boosting for tumor classification with gene expression data","volume":"19","author":"Dettling","year":"2003","journal-title":"Bioinformatics"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1145\/321941.321956","article-title":"Picture segmentation by a tree traversal algorithm","volume":"23","author":"Horowitz","year":"1976","journal-title":"JACM"},{"key":"ref_51","unstructured":"Heath, M.D., Bowyer, K.W., Kopans, D., Kegelmeyer, P., Moore, R., Chang, K., and Munishkumaran, S. (1998). Digital Mammography, Kluwer Academic Publishers."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/2\/4\/1503\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T22:11:51Z","timestamp":1760220711000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/2\/4\/1503"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,12,1]]},"references-count":51,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2009,12]]}},"alternative-id":["a2041503"],"URL":"https:\/\/doi.org\/10.3390\/a2041503","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,12,1]]}}}