Abstract
Tomosynthesis as a technique is being developed and studied with the goal of overcoming mammography’s limitations due to overlying tissue. Various algorithms exist for tomosynthesis datasets including a novel Computer Aided Detection (CADe) algorithm using a featureless False Positive (FP) reduction stage. The goal of this project is to study the previously unexplored effects of variation of Region of Interest (ROI) sizes as well as the crucial similarity metrics for such a CADe algorithm’s performance. Four datasets consisting of 1479 tomosynthesis ROIs were generated by a CADe algorithm from reconstructed volumes of one hundred subjects consisting of 4 different sizes – 128 x 128, 256 x 256, 512 x 512, and 1024 x 1024 pixels. Five different similarity metrics – (1) mutual information, (2) average conditional entropy, (3) joint entropy, (3) Jensen divergence and (4) average Kullback-Leibler divergence were used for the task of FP reduction using a leave-one-case-out sampling scheme. Mutual information and average conditional entropy were the best performing metrics with an Area Under Curve (AUC) of 0.88. Cross-bin measures performed consistently higher than those that rely on only marginal distributions. Also, for all metrics, the datatset consisting of 256 x 256 pixel ROIs gave the best performance. In conclusion, for the tomosynthesis dataset, cross-bin measures such as MI and average conditional entropy should be used over other metrics using a ROI size of 256 x 256 pixels.
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
Reiser, I., Nishikawa, R.M., Giger, M.L., Wu, T., Rafferty, E.A., Moore, R., Kopans, D.B.: Computerized mass detection for digital breast tomosynthesis directly from the projection images. Med. Phys. 33, 482–491 (2006)
Reiser, I.S., Sidky, E.Y., Giger, M.L., Nishikawa, R.M., Rafferty, E.A., Kopans, D.B., Moore, R., Wu, T.: A reconstruction-independent method for computerized mass detection in digital tomosynthesis images of the breast. In: Medical Imaging 2004: Image Processing, vol. 5370, pp. 833–838. SPIE, San Diego (2004)
Chan, H.-P., Wei, J., Zhang, Y., Moore, R.H., Kopans, D.B., Hadjiiski, L., Sahiner, B., Roubidoux, M.A., Helvie, M.A.: Computer-aided detection of masses in digital tomosynthesis mammography: combination of 3D and 2D detection information. In: Medical Imaging 2007: Computer-Aided Diagnosis, vol. 6514, p. 651416. SPIE, San Diego (2007)
Wheeler, F.W., Perera, A.G.A., Claus, B.E., Muller, S.L., Peters, G., Kaufhold, J.P.: Micro-calcification detection in digital tomosynthesis mammography. In: Medical Imaging 2006: Image Processing, vol. 6144, pp. 614420–614412. SPIE, San Diego (2006)
Bernard, S., Muller, S., Peters, G., Iordache, R.: Fast microcalcification detection on digital breast tomosynthesis datasets. In: Medical Imaging 2007: Computer-Aided Diagnosis, vol. 6514, pp. 65141X–65148. SPIE, San Diego (2007)
Peters, G., Muller, S., Grosjean, B., Bernard, S., Bloch, I.: A hybrid active contour model for mass detection in digital breast tomosynthesis. In: Medical Imaging 2007: Computer-Aided Diagnosis, vol. 6514, pp. 65141V–65111. SPIE, San Diego (2007)
Peters, G., Muller, S., Bernard, S., Iordache, R., Bloch, I.: Reconstruction-independent 3D CAD for mass detection in digital breast tomosynthesis using fuzzy particles. In: Medical Imaging 2006: Image Processing, vol. 6144, pp. 61441Z–61410. SPIE, San Diego (2006)
Tourassi, G.D., Vargas-Voracek, R., Catarious, D.M.: Jr: Computer-assisited detection of mammographic masses: a template matching scheme based on mutual information. Med. Phys. 30, 2123–2130 (2003)
Tourassi, G.D., Harrawood, B., Singh, S., Lo, J.Y.: Information-theoretic CAD system in mammography: Entropy-based indexing for computational efficiency and robust performance. Med. Phys. 34, 3193–3204 (2007)
Tourassi, G.D., Harrawood, B., Singh, S., Lo, J.Y., Floyd Jr., C.E.: Evaluation of information-theoretic similarity measures for content-based retrieval and detection of masses in mammograms. Med. Phys. 34, 140–150 (2007)
Tourassi, G.D., Vargas-Voracek, R., Catarious Jr., D.M., Floyd Jr., C.E.: Computer-assisted detection of mammographic masses: A template matching scheme based on mutual information. Med. Phys. 30, 2123–2130 (2003)
Tourassi, G.D., Floyd Jr., C.E.: Knowledge-based detection of mammographic masses: analysis of the impact of database comprehensiveness. In: Medical Imaging 2005: PACS and Imaging Informatics, vol. 5748, pp. 399–406. SPIE, San Diego (2005)
Singh, S., Tourassi, G.D., Lo, J.Y.: Breast mass detection in tomosynthesis projection images using information-theoretic similarity measures. In: Giger, M.L., Karssemeijer, N. (eds.) SPIE Medical Imaging 2007: Computer-Aided Diagnosis, San Diego, CA, vol. 6515 (2007)
Ike Iii, R.C., Singh, S., Harrawood, B., Tourassi, G.D.: Effect of ROI size on the performance of an information-theoretic CAD system in mammography: multi-size fusion analysis. In: Medical Imaging 2008: Computer-Aided Diagnosis, vol. 6915, p. 691527. SPIE, San Diego (2008)
Singh, S., Tourassi, G.D., Chawla, A.S., Saunders, R.S., Samei, E., Lo, J.Y.: Computer-aided detection of breast masses in tomosynthesis reconstructed volumes using information-theoretic similarity measures. In: Medical Imaging 2008: Computer-Aided Diagnosis, vol. 6915, pp. 691505–691508. SPIE, San Diego (2008)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Singh, S., Tourassi, G.D., Lo, J.Y. (2008). Effect of Similarity Metrics and ROI Sizes in Featureless Computer Aided Detection of Breast Masses in Tomosynthesis. In: Krupinski, E.A. (eds) Digital Mammography. IWDM 2008. Lecture Notes in Computer Science, vol 5116. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70538-3_40
Download citation
DOI: https://doi.org/10.1007/978-3-540-70538-3_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70537-6
Online ISBN: 978-3-540-70538-3
eBook Packages: Computer ScienceComputer Science (R0)