Abstract
We present a method based on the content-based image retrieval (CBIR) paradigm to enhance the performance of computer aided detection (CAD) in computed tomographic colonography (CTC). The method explores curvature-based feature descriptors in conjunction with bag-of-words (BoW) models to characterize colonic detections. The diffusion distance is adopted to improve feature matching and clustering. Word selection is also applied to remove non-informative words. A representative database is constructed to categorize different types of detections. Query detections are compared with the database for classification. We evaluated the performance of the system by using digital phantoms of common structures in the colon as well as real CAD detections. The results demonstrated the potential of our technique for distinguishing common structures within the colon as well as for classifying true and false-positive CAD detections.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Summers, R.M., et al.: Computed Tomographic Virtual Colonoscopy Computer-Aided Polyp Detection in a Screening Population. Gastroenterology 129, 1832–1844 (2005)
Muller, H., et al.: Review of content-based image retrieval systems in medical applications—clinical benefits and future directions. International Journal of Medical Informatics 72, 1–23 (2004)
Guicca, G., Schettini, R.: A relevance feedback mechanism for content-based image retrieval. Info. Proc. and Manag. 35, 605–632 (1999)
Yang, J., et al.: Evaluating bag-of-visual-words representations in scene classification. In: International Workshop on Multimedia Information Retrieval. ACM, Augsburg (2007)
Cheung, W., Hamarneh, G.: n-SIFT: n-Dimensional Scale Invariant Feature Transform. IEEE Transactions on Image Processing 18(9), 2012–2021 (2009)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)
Koenderink, J.J., van Doorn, A.J.: Surface shape and curvature scales. Image and Vision Computing 10(8), 557–565 (1992)
Ling, H., Okada, K.: Diffusion Distance for Histogram Comparison. In: IEEE Conference on Computer Vision and Pattern Recognition, New York, USA (2006)
Kanungo, T., et al.: An Efficient k-Means Clustering Algorithm: Analysis and Implementation. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(7), 881–892 (2003)
Croft, B., Metzler, D., Strohman, T.: Search Engines: Information Retrieval in Practice. Addison Wesley (2009)
ROCKIT, Kurt Rossman Laboratories. University of Chicago, Chicago, IL (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aman, J.M., Summers, R.M., Yao, J. (2011). Characterizing Colonic Detections in CT Colonography Using Curvature-Based Feature Descriptor and Bag-of-Words Model. In: Yoshida, H., Cai, W. (eds) Virtual Colonoscopy and Abdominal Imaging. Computational Challenges and Clinical Opportunities. ABD-MICCAI 2010. Lecture Notes in Computer Science, vol 6668. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25719-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-25719-3_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25718-6
Online ISBN: 978-3-642-25719-3
eBook Packages: Computer ScienceComputer Science (R0)