{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T07:02:58Z","timestamp":1791097378715,"version":"4.1.0"},"reference-count":39,"publisher":"SPIE-Intl Soc Optical Eng","issue":"01","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Electron. Imag."],"published-print":{"date-parts":[[2003,1,1]]},"abstract":"<jats:p>Recently, research in the field of content-based image retrieval has attracted a lot of attention. Nevertheless, most existing methods cannot be easily applied to medical image databases, as global image descriptions based on color, texture, or shape do not supply sufficient semantics for medical applications. The concept for content-based image retrieval in medical applications (IRMA) is therefore based on the separation of the following processing steps: categorization of the entire image; registration with respect to prototypes; extraction and query-dependent selection of local features; hierarchical blob representation including object identification; and finally, image retrieval. Within the first step of processing, images are classified according to image modality, body orientation, anatomic region, and biological system. The statistical classifier for the anatomic region is based on Gaussian kernel densities within a probabilistic framework for multiobject recognition. Special emphasis is placed on invariance, employing a probabilistic model of variability based on tangent distance and an image distortion model. The performance of the classifier is evaluated using a set of 1617 radiographs from daily routine, where the error rate of 8.0% in this six-class problem is an excellent result, taking into account the difficulty of the task. The computed posterior probabilities are furthermore used in the subsequent steps of the retrieval process.<\/jats:p>","DOI":"10.1117\/1.1525790","type":"journal-article","created":{"date-parts":[[2003,1,30]],"date-time":"2003-01-30T15:42:55Z","timestamp":1043941375000},"page":"59-68","source":"Crossref","is-referenced-by-count":81,"title":["Statistical framework for model-based image retrieval in medical applications"],"prefix":"10.1117","volume":"12","author":[{"given":"Daniel","family":"Keysers","sequence":"first","affiliation":[{"name":"RWTH-Aachen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joerg","family":"Dahmen","sequence":"additional","affiliation":[{"name":"Rheinisch-Westfaelische Technische Hochschule Aach"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[{"name":"RWTH-Aachen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Berthold B.","family":"Wein","sequence":"additional","affiliation":[{"name":"RWTH-Aachen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas M.","family":"Lehmann","sequence":"additional","affiliation":[{"name":"RWTH-Aachen"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","reference":[{"key":"10.1117\/1.1525790_r1","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1117\/12.143648","volume":"1908","author":"Niblack","year":"1993","journal-title":"Proc. SPIE","ISSN":"https:\/\/id.crossref.org\/issn\/0277-786X","issn-type":"print"},{"key":"10.1117\/1.1525790_r2","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1117\/12.171786","volume":"2185","author":"Pentland","year":"1994","journal-title":"Proc. SPIE","ISSN":"https:\/\/id.crossref.org\/issn\/0277-786X","issn-type":"print"},{"key":"10.1117\/1.1525790_r3","doi-asserted-by":"crossref","unstructured":"C. Carson, M. Thomas, S. Belongie, J. Hellerstein, and J. Malik, \u201cBlobworld: a system for region-based image indexing and retrieval,\u201d in\n                      Proc. 3rd Int. Conf. Visual Information Systems\n                      , Vol. 1614 of LNCS, pp. 509\u2013516, Springer, Amsterdam, The Netherlands (June 1999).","DOI":"10.1007\/3-540-48762-X_63"},{"key":"10.1117\/1.1525790_r4","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1117\/12.234781","volume":"2670","author":"Smith","year":"1996","journal-title":"Proc. SPIE","ISSN":"https:\/\/id.crossref.org\/issn\/0277-786X","issn-type":"print"},{"key":"10.1117\/1.1525790_r5","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/S0262-8856(96)01114-6","volume":"15","author":"de Marsico","year":"1997","journal-title":"Image Vis. Comput.","ISSN":"https:\/\/id.crossref.org\/issn\/0262-8856","issn-type":"print"},{"key":"10.1117\/1.1525790_r6","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1109\/34.895972","volume":"22","author":"Smeulders","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.","ISSN":"https:\/\/id.crossref.org\/issn\/0162-8828","issn-type":"print"},{"key":"10.1117\/1.1525790_r7","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/BF00962238","volume":"3","author":"Faloutsos","year":"1994","journal-title":"J. Intell. Inf. Syst.","ISSN":"https:\/\/id.crossref.org\/issn\/0925-9902","issn-type":"print"},{"key":"10.1117\/1.1525790_r8","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/34.589215","volume":"19","author":"Schmid","year":"1997","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.","ISSN":"https:\/\/id.crossref.org\/issn\/0162-8828","issn-type":"print"},{"key":"10.1117\/1.1525790_r9","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1117\/12.373563","volume":"3972","author":"Lehmann","year":"2000","journal-title":"Proc. SPIE","ISSN":"https:\/\/id.crossref.org\/issn\/0277-786X","issn-type":"print"},{"key":"10.1117\/1.1525790_r10","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1016\/S0262-8856(98)00084-5","volume":"16","author":"Nappi","year":"1998","journal-title":"Image Vis. Comput.","ISSN":"https:\/\/id.crossref.org\/issn\/0262-8856","issn-type":"print"},{"key":"10.1117\/1.1525790_r11","unstructured":"Y. Liu and F. Dellaert, \u201cA classification based similarity metric for 3D image retrieval,\u201d in\n                      Proc. Int. Conf. Computer Vision and Pattern Recognition\n                      , pp. 800\u2013805, IEEE, Santa Barbara, CA (June 1998)."},{"key":"10.1117\/1.1525790_r12","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1109\/69.738356","volume":"10","author":"Korn","year":"1998","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1117\/1.1525790_r13","unstructured":"H. Burkhardt and S. Siggelkow, \u201cInvariant features in pattern recognition\u2014fundamentals and applications,\u201d in\n                      Nonlinear Model-Based Image\/Video Processing and Analysis,\n                      C. Kotropoulos and I. Pitas, Eds., pp. 269\u2013307, Wiley, New York (2001)."},{"key":"10.1117\/1.1525790_r14","doi-asserted-by":"crossref","unstructured":"M. Ankerst, G. Kastenmu\u0308ller, H.-P. Kriegel, and T. Seidl, \u201c3D shape histograms for similarity search and classification in spatial databases,\u201d in\n                      Proc. 6th Int. Symp. on Spatial Databases\n                      , Vol. 1651 of\n                      LNCS\n                      , pp. 207\u2013226, Springer, Hong Kong, China (July 1999).","DOI":"10.1007\/3-540-48482-5_14"},{"key":"10.1117\/1.1525790_r15","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1006\/cviu.1999.0768","volume":"75","author":"Shyu","year":"1999","journal-title":"Comput. Vis. Image Underst.","ISSN":"https:\/\/id.crossref.org\/issn\/1077-3142","issn-type":"print"},{"key":"10.1117\/1.1525790_r16","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1109\/69.738355","volume":"10","author":"Chu","year":"1998","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1117\/1.1525790_r17","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1136\/jamia.1997.0040184","volume":"4","author":"Tagare","year":"1997","journal-title":"J. Am. Med. Inform Assoc.","ISSN":"https:\/\/id.crossref.org\/issn\/1067-5027","issn-type":"print"},{"key":"10.1117\/1.1525790_r18","doi-asserted-by":"crossref","unstructured":"M. Kohnen, H. Schubert, B. B. Wein, R. W. Gu\u0308nther, J. Bredno, T. M. Lehmann, and J. Dahmen, \u201cQualita\u0308t von DICOM-Informationen in Bilddaten aus der klinischen Routine,\u201d in\n                      Bildverarbeitung fu\u0308r die Medizin 2001\n                      , pp. 419\u2013423, Springer, Lu\u0308beck, Germany (Mar. 2001).","DOI":"10.1007\/978-3-642-56714-8_78"},{"key":"10.1117\/1.1525790_r19","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1117\/12.310945","volume":"3338","author":"Weiler","year":"1998","journal-title":"Proc. SPIE","ISSN":"https:\/\/id.crossref.org\/issn\/0277-786X","issn-type":"print"},{"key":"10.1117\/1.1525790_r20","unstructured":"J. Goldstein, R. Ramakrishnan, U. Shaft, and J. B. Yu, \u201cUsing constraints to query R\u22c6-trees,\u201d Technical report 1301, Dept. of Computer Science, University of Wisconsin, Madison (Feb. 1996)."},{"key":"10.1117\/1.1525790_r21","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/5.880081","volume":"88","author":"Ney","year":"2000","journal-title":"Proc. IEEE","ISSN":"https:\/\/id.crossref.org\/issn\/0018-9219","issn-type":"print"},{"key":"10.1117\/1.1525790_r22","unstructured":"J. Dahmen, T. Theiner, D. Keysers, H. Ney, T. Lehmann, and B. Wein, \u201cClassification of radiographs in the \u2018image retrieval in medical applications\u2019 system (IRMA),\u201d in\n                      Proc. 6th Int. RIAO Conf. on Content-Based Multimedia Information Access,\n                      pp. 551\u2013566, Paris, France (Apr. 2000)."},{"key":"10.1117\/1.1525790_r23","unstructured":"R. O. Duda, P. E. Hart, and D. G. Stork,\n                      Pattern Classification\n                      , 2nd. ed., Wiley, New York (2001)."},{"key":"10.1117\/1.1525790_r24","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1023\/A:1011242314266","volume":"14","author":"Dahmen","year":"2001","journal-title":"J. Math. Imaging Vision","ISSN":"https:\/\/id.crossref.org\/issn\/0924-9907","issn-type":"print"},{"key":"10.1117\/1.1525790_r25","doi-asserted-by":"crossref","unstructured":"D. Keysers, W. Macherey, J. Dahmen, and H. Ney, \u201cLearning of variability for invariant statistical pattern recognition,\u201d in\n                      ECML 2001, 12th Eur. Conf. on Machine Learning\n                      , Vol. 2167 of LNCS, pp. 263\u2013275, Springer, Freiburg (Sep. 2001).","DOI":"10.1007\/3-540-44795-4_23"},{"key":"10.1117\/1.1525790_r26","unstructured":"P. Simard, Y. Le Cun, and J. Denker, \u201cEfficient pattern recognition using a new transformation distance,\u201d in\n                      Advances in Neural Information Processing Systems 5\n                      , S. Hanson, J. Cowan, and C. Giles, Eds., pp. 50\u201358, Morgan Kaufmann, San Mateo, CA (1993)."},{"key":"10.1117\/1.1525790_r27","doi-asserted-by":"crossref","unstructured":"D. Keysers, J. Dahmen, T. Theiner, and H. Ney, \u201cExperiments with an extended tangent distance,\u201d in\n                      Proc. 15th Int. Conf. on Pattern Recognition\n                      , Vol. 2, pp. 38\u201342, IEEE, Barcelona, Spain (Sep. 2000).","DOI":"10.1109\/ICPR.2000.906014"},{"key":"10.1117\/1.1525790_r28","doi-asserted-by":"crossref","unstructured":"J. Dahmen, D. Keysers, M. Motter, H. Ney, T. Lehmann, and B. Wein, \u201cAn automatic approach to invariant radiograph classification,\u201d in\n                      Bildverarbeitung fu\u0308r die Medizin 2001\n                      , pp. 337\u2013341, Springer, Lu\u0308beck, Germany (Mar. 2001).","DOI":"10.1007\/978-3-642-56714-8_62"},{"key":"10.1117\/1.1525790_r29","doi-asserted-by":"crossref","unstructured":"S. Uchida and H. Sakoe, \u201cA monotonic and continuous two-dimensional warping based on dynamic programming,\u201d in\n                      Proc. 14th Int. Conf. on Pattern Recognition\n                      , Vol. 1, pp. 521\u2013524, IEEE, Brisbane, Australia (Aug. 1998).","DOI":"10.1109\/ICPR.1998.711195"},{"key":"10.1117\/1.1525790_r30","unstructured":"N. Vasconcelos and A. Lippman, \u201cMultiresolution tangent distance for affine-invariant classification,\u201d in\n                      Advances in Neural Inf. Proc. Systems\n                      , M. I. Jordan, M. J. Kearns, and S. A. Solla, Eds., Vol. 10, pp. 843\u2013849, MIT Press, Cambridge, MA (1998)."},{"key":"10.1117\/1.1525790_r31","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","volume":"3","author":"Haralick","year":"1973","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"10.1117\/1.1525790_r32","doi-asserted-by":"crossref","unstructured":"H. Haken,\n                      Synergetic Computers and Cognition\n                      , Springer Verlag, New York (1991).","DOI":"10.1007\/978-3-662-22450-2"},{"key":"10.1117\/1.1525790_r33","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1117\/12.274187","volume":"3034","author":"Weiler","year":"1997","journal-title":"Proc. SPIE","ISSN":"https:\/\/id.crossref.org\/issn\/0277-786X","issn-type":"print"},{"key":"10.1117\/1.1525790_r34","unstructured":"G. Hinton, Z. Ghahramani, and Y. Teh, \u201cLearning to parse images,\u201d in\n                      Advances in Neural Information Processing Systems 12\n                      , S. Solla, T. Leen, and K. Mu\u0308ller, Eds., pp. 463\u2013469, MIT Press, Cambridge, MA (2000)."},{"key":"10.1117\/1.1525790_r35","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1109\/34.615452","volume":"19","author":"Mardia","year":"1997","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.","ISSN":"https:\/\/id.crossref.org\/issn\/0162-8828","issn-type":"print"},{"key":"10.1117\/1.1525790_r36","doi-asserted-by":"crossref","unstructured":"J. Po\u0308sl and H. Niemann, \u201cWavelet features for statistical object localization without segmentation,\u201d in\n                      Proc. Int. Conf. on Image Processing\n                      , pp. 170\u2013173, IEEE, Santa Barbara, CA (1997).","DOI":"10.1109\/ICIP.1997.632041"},{"key":"10.1117\/1.1525790_r37","doi-asserted-by":"crossref","unstructured":"M. Reinhold, D. Paulus, and H. Niemann, \u201cAppearance-based statistical object recognition by heterogeneous background and occlusions,\u201d in\n                      Pattern Recognition, 23rd DAGM Symp.\n                      , Vol. 2191 of\n                      LNCS\n                      , pp. 254\u2013261, Springer, Munich, Germany (2001).","DOI":"10.1007\/3-540-45404-7_34"},{"key":"10.1117\/1.1525790_r38","doi-asserted-by":"crossref","unstructured":"S. Akaho, \u201cThe EM algorithm for multiple object recognition,\u201d in\n                      Proc. Int. Conf. on Neural Networks ICNN\u201995\n                      , pp. 2426\u20132431, IEEE, Perth, Australia (Nov. 1995).","DOI":"10.1109\/ICNN.1995.487742"},{"key":"10.1117\/1.1525790_r39","doi-asserted-by":"crossref","unstructured":"S. Uchida and H. Sakoe, \u201cPiecewise linear two-dimensional warping,\u201d in\n                      Proc. 15th Int. Conf. on Pattern Recognition,\n                      Vol. 3, pp. 538\u2013541, IEEE, Barcelona, Spain (Sep. 2000).","DOI":"10.1109\/ICPR.2000.903601"}],"container-title":["Journal of Electronic Imaging"],"original-title":[],"link":[{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-electronic-imaging\/volume-12\/issue-01\/59\/Statistical-framework-for-model-based-image-retrieval-in-medical-applications\/10.1117\/1.1525790.full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T21:29:13Z","timestamp":1790890153000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-electronic-imaging\/volume-12\/issue-01\/59\/Statistical-framework-for-model-based-image-retrieval-in-medical-applications\/10.1117\/1.1525790.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,1,1]]},"references-count":39,"journal-issue":{"issue":"01"},"URL":"https:\/\/doi.org\/10.1117\/1.1525790","relation":{},"ISSN":["1017-9909","1560-229X"],"issn-type":[{"value":"1017-9909","type":"print"},{"value":"1560-229X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2003,1,1]]}}}