A boosting framework for visuality-preserving distance metric learning and its application to medical image retrieval
- PMID: 19926897
- DOI: 10.1109/TPAMI.2008.273
A boosting framework for visuality-preserving distance metric learning and its application to medical image retrieval
Abstract
Similarity measurement is a critical component in content-based image retrieval systems, and learning a good distance metric can significantly improve retrieval performance. However, despite extensive study, there are several major shortcomings with the existing approaches for distance metric learning that can significantly affect their application to medical image retrieval. In particular, "similarity" can mean very different things in image retrieval: resemblance in visual appearance (e.g., two images that look like one another) or similarity in semantic annotation (e.g., two images of tumors that look quite different yet are both malignant). Current approaches for distance metric learning typically address only one goal without consideration of the other. This is problematic for medical image retrieval where the goal is to assist doctors in decision making. In these applications, given a query image, the goal is to retrieve similar images from a reference library whose semantic annotations could provide the medical professional with greater insight into the possible interpretations of the query image. If the system were to retrieve images that did not look like the query, then users would be less likely to trust the system; on the other hand, retrieving images that appear superficially similar to the query but are semantically unrelated is undesirable because that could lead users toward an incorrect diagnosis. Hence, learning a distance metric that preserves both visual resemblance and semantic similarity is important. We emphasize that, although our study is focused on medical image retrieval, the problem addressed in this work is critical to many image retrieval systems. We present a boosting framework for distance metric learning that aims to preserve both visual and semantic similarities. The boosting framework first learns a binary representation using side information, in the form of labeled pairs, and then computes the distance as a weighted Hamming distance using the learned binary representation. A boosting algorithm is presented to efficiently learn the distance function. We evaluate the proposed algorithm on a mammographic image reference library with an Interactive Search-Assisted Decision Support (ISADS) system and on the medical image data set from ImageCLEF. Our results show that the boosting framework compares favorably to state-of-the-art approaches for distance metric learning in retrieval accuracy, with much lower computational cost. Additional evaluation with the COREL collection shows that our algorithm works well for regular image data sets.
Similar articles
-
Modeling semantic aspects for cross-media image indexing.IEEE Trans Pattern Anal Mach Intell. 2007 Oct;29(10):1802-17. doi: 10.1109/TPAMI.2007.1097. IEEE Trans Pattern Anal Mach Intell. 2007. PMID: 17699924
-
Learning semantic and visual similarity for endomicroscopy video retrieval.IEEE Trans Med Imaging. 2012 Jun;31(6):1276-88. doi: 10.1109/TMI.2012.2188301. Epub 2012 Feb 16. IEEE Trans Med Imaging. 2012. PMID: 22353403
-
Content-based histopathology image retrieval using a kernel-based semantic annotation framework.J Biomed Inform. 2011 Aug;44(4):519-28. doi: 10.1016/j.jbi.2011.01.011. Epub 2011 Feb 3. J Biomed Inform. 2011. PMID: 21296682
-
A review of content-based image retrieval systems in medical applications-clinical benefits and future directions.Int J Med Inform. 2004 Feb;73(1):1-23. doi: 10.1016/j.ijmedinf.2003.11.024. Int J Med Inform. 2004. PMID: 15036075 Review.
-
Rough sets and near sets in medical imaging: a review.IEEE Trans Inf Technol Biomed. 2009 Nov;13(6):955-68. doi: 10.1109/TITB.2009.2017017. Epub 2009 Mar 16. IEEE Trans Inf Technol Biomed. 2009. PMID: 19304490 Review.
Cited by
-
An interactive system for computer-aided diagnosis of breast masses.J Digit Imaging. 2012 Oct;25(5):570-9. doi: 10.1007/s10278-012-9451-0. J Digit Imaging. 2012. PMID: 22234836 Free PMC article.
-
A multi-level similarity measure for the retrieval of the common CT imaging signs of lung diseases.Med Biol Eng Comput. 2020 May;58(5):1015-1029. doi: 10.1007/s11517-020-02146-4. Epub 2020 Mar 2. Med Biol Eng Comput. 2020. PMID: 32124223 Free PMC article.
-
Content-based image retrieval of digitized histopathology in boosted spectrally embedded spaces.J Pathol Inform. 2015 Jun 29;6:41. doi: 10.4103/2153-3539.159441. eCollection 2015. J Pathol Inform. 2015. PMID: 26167385 Free PMC article.
-
Content-based medical image retrieval: a survey of applications to multidimensional and multimodality data.J Digit Imaging. 2013 Dec;26(6):1025-39. doi: 10.1007/s10278-013-9619-2. J Digit Imaging. 2013. PMID: 23846532 Free PMC article. Review.
-
Adaptive distance metric learning for diffusion tensor image segmentation.PLoS One. 2014 Mar 20;9(3):e92069. doi: 10.1371/journal.pone.0092069. eCollection 2014. PLoS One. 2014. PMID: 24651858 Free PMC article.
Publication types
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical