Image analysis – Learning systems – Trainable classifiers or pattern recognizers
Reexamination Certificate
2011-07-26
2011-07-26
Mehta, Bhavesh M (Department: 2624)
Image analysis
Learning systems
Trainable classifiers or pattern recognizers
C382S224000, C382S128000, C706S020000
Reexamination Certificate
active
07986827
ABSTRACT:
A method of training a classifier for computer aided detection of digitized medical image, includes providing a plurality of bags, each bag containing a plurality of feature samples of a single region-of-interest in a medical image, where each region-of-interest has been labeled as either malignant or healthy. The training uses candidates that are spatially adjacent to each other, modeled by a “bag”, rather than each candidate by itself. A classifier is trained on the plurality of bags of feature samples, subject to the constraint that at least one point in a convex hull of each bag, corresponding to a feature sample, is correctly classified according to the label of the associated region-of-interest, rather than a large set of discrete constraints where at least one instance in each bag has to be correctly classified.
REFERENCES:
patent: 5465308 (1995-11-01), Hutcheson et al.
patent: 5544256 (1996-08-01), Brecher et al.
patent: 5598509 (1997-01-01), Takahashi et al.
patent: 5835901 (1998-11-01), Duvoisin et al.
patent: 5923837 (1999-07-01), Matias
patent: 5943056 (1999-08-01), Sato et al.
patent: 5987445 (1999-11-01), Rao et al.
patent: 6018590 (2000-01-01), Gaborski
patent: 6205348 (2001-03-01), Giger et al.
patent: 6269176 (2001-07-01), Barski et al.
patent: 6317517 (2001-11-01), Lu
patent: 6609021 (2003-08-01), Fan et al.
patent: 6629065 (2003-09-01), Gadh et al.
patent: 6630660 (2003-10-01), Finn
patent: 6678413 (2004-01-01), Liang et al.
patent: 6750964 (2004-06-01), Levenson et al.
patent: 7024033 (2006-04-01), Li et al.
patent: 7092749 (2006-08-01), Fowkes et al.
patent: 7099505 (2006-08-01), Li et al.
patent: 7263214 (2007-08-01), Uppaluri et al.
patent: 7295691 (2007-11-01), Uppaluri et al.
patent: 7346201 (2008-03-01), Ashton
patent: 7463773 (2008-12-01), Lee et al.
patent: 7536044 (2009-05-01), Zhou et al.
patent: 7650321 (2010-01-01), Krishnan et al.
patent: 7702596 (2010-04-01), Tu et al.
patent: 7796795 (2010-09-01), Uppaluri et al.
patent: 2001/0043729 (2001-11-01), Giger et al.
patent: 2002/0069206 (2002-06-01), Bergman et al.
patent: 2003/0215119 (2003-11-01), Uppaluri et al.
patent: 2003/0215120 (2003-11-01), Uppaluri et al.
patent: 2004/0101181 (2004-05-01), Giger et al.
patent: 2004/0131254 (2004-07-01), Liang et al.
patent: 2004/0165767 (2004-08-01), Gokturk et al.
patent: 2005/0010106 (2005-01-01), Lang et al.
patent: 2005/0069183 (2005-03-01), Ashton
patent: 2005/0096539 (2005-05-01), Leibig et al.
patent: 2005/0177040 (2005-08-01), Fung et al.
patent: 2005/0209519 (2005-09-01), Krishnan et al.
patent: 2006/0045337 (2006-03-01), Shilman et al.
patent: 2006/0064017 (2006-03-01), Krishnan et al.
patent: 2006/0074908 (2006-04-01), Selvaraj et al.
patent: 2006/0184475 (2006-08-01), Krishnan et al.
patent: 2006/0222221 (2006-10-01), Sathyanarayana
patent: 2006/0247514 (2006-11-01), Panasyuk et al.
patent: 2006/0271556 (2006-11-01), Mukherjee et al.
patent: 2007/0011121 (2007-01-01), Bi et al.
patent: 2007/0081710 (2007-04-01), Hong et al.
patent: 2007/0110292 (2007-05-01), Bi et al.
patent: 2007/0280530 (2007-12-01), Fung et al.
patent: 2008/0031507 (2008-02-01), Uppaluri et al.
patent: 2008/0109388 (2008-05-01), Rosales et al.
patent: 2008/0118124 (2008-05-01), Madabhushi et al.
patent: 2008/0301077 (2008-12-01), Fung et al.
patent: 2008/0317308 (2008-12-01), Wu et al.
patent: 2009/0080731 (2009-03-01), Krishnapuram et al.
patent: 2009/0180669 (2009-07-01), Horovitz et al.
patent: 2011/0026798 (2011-02-01), Madabhushi et al.
Fung et al Multiple Instance Learning for Computer Aided Diagnosis—pp. 1-8.
Pudil et al Novel Methods for Subset Selection with Respect to Problem Knowledge—pp. 1-9.
Dhillon et al. “Class Visualization of High Dimensional Data With Applications” Computational Stats and Data Analysis, 2002, vol. 41, pp. 59-90.
Iwata et al. “Parametrix Embedding of Class Visualization” Neural Computation 19, 2356-2556, 2004.
Globerson er al. “Euclidean Embedding of Co-Occurence Data” NIPS, 2004.
Mika et al., “A Mathematical Programming Approach to the Kernel Fisher Algorithm”, Advances in Neural Information Processing Systems 13, pp. 591-597.MIT Press, 2001.
Mangasarian, “Generalized Support Vector Machines”, Mathematical Programming Technical Report 98-14, Oct. 1998, http://www.cs.wisc.edu/˜olvi/.
Lee et al, “RSVM: Reduced Support Vector Machines”, Data Mining Institute Technical Report 00-07, Jul. 2000, CD Proceedings of the SIAM International Conference on Data Mining, Chicago, Apr. 5-7, 2001, SIAM, Philadelphia, ISBN 0-89871-495-8, http://www.cs.wisc.edu/˜olvi/.
Mangasarian et al, “Multiple Instance Classification via Successive Linear Programming”, Data Mining Institute Technical Report 05-02, May 2005, http://www.cs.wisc.edu/˜olvi/.
Bezdek et al., “Some Notes on Alternating Optimization” N.R Pal and M. Sugeno (Eds.): AFSS 2002, LNAI 2275, pp. 289-300, 2002.
Fung et al., “Multiple Instance Learning for Computer Aided Diagnosis”, Neural Information Processing Systems, Dec. 4, 2006.
Managasarian et al., “Multiple Instance Classification Via Successive Linear Programming”, Data Mining Institute Technical Report 05-02, University of Wisconsin Madison, Feb. 2005, retrieved from the internet: URL:ftp://ftp.cs.wisc.edu/pub/dmi/tech-reports/05-02.pdf.
Fung et al., “Knowledge-Based Support Vector Machine Classifiers”, Proceedings of International Conference on Neural Information Processing, 2002, pp. 1-8.
Dundar Murat
Fung Glenn
Krishnapuram Balaji
Rao R. Bharat
Mehta Bhavesh M
Siemens Medical Solutions USA , Inc.
Thomas Mia M
Withstandley Peter
LandOfFree
System and method for multiple instance learning for... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for multiple instance learning for..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for multiple instance learning for... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2710109