Abstract
This study investigates the effectiveness of CAD for low-conspicuity malignant lesions that are subtle and sometimes missed in conventional analysis. 280 malignantcases were retrospectively reviewed by a non-blinded radiologist, who identified 676 findings. A conspicuity score was assigned to each finding on each view, and 171 findings were of low conspicuity. CAD sensitivity of a prototype CAD algorithm (Siemens), for the high-conspicuity findings was 91.5%. The sensitivity for the 67 cases with low-conspicuity findings in both views (65.7%) was considerably higher than that reported for similar cases in conventional interpretation (40.2%). For the 2688 normal cases, CAD generated 1.24 false marks per case. CAD sensitivity for low-conspicuity findings did not significantly depend on breast density, and was significantly better for non-invasive lesions and for masses in younger women. Thus, CAD should be most beneficial for avoiding oversight of low-conspicuity breast cancers, particularly non-invasive lesions and masses in younger women.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Birdwell, R.L., Bandodkar, P., Ikeda, D.M.: Computer-aided detection with screening mammography in a university hospital setting. Radiology 236, 451–457 (2005)
Romero, C., Almenar, A., Pinto, J.M., Varela, C., Muñoz, E., Botella, M.: Impact on breast cancer diagnosis in a multidisciplinary unit after the incorporation of mammography digitalization and computer-aided detection systems. Am. J. Roentgenol. 197(6), 1492–1497 (2011)
Fenton, J.J., Abraham, L., Taplin, S.H., Geller, B.M., Carney, P.A., D’Orsi, C., Elmore, J.G., Barlow, W.E.: Breast Cancer Surveillance Consortium. Effectiveness of computer-aided detection in community mammography practice. J. Natl. Cancer Inst. 103(15), 1152–1161 (2011)
Bamberger, P., Leichter, I., Merlet, N., Ratner, E., Fung, G., Lederman, R.: Optimizing the CAD Process for Detecting Mammographic Lesions by a New Generation Algorithm Using Linear Classifiers and a Gradient Based Approach. In: Krupinski, E.A. (ed.) IWDM 2008. LNCS, vol. 5116, pp. 358–365. Springer, Heidelberg (2008)
Leichter, I., Lederman, R., Ratner, E., Merlet, N., Fung, G., Krishnapuram, B., Bamberger, P.: Does a Mammography CAD Algorithm with Varying Filtering Levels of Detection Marks, Used to Reduce the False Mark Rate, Adversely Affect the Detection of Small Masses? In: Krupinski, E.A. (ed.) IWDM 2008. LNCS, vol. 5116, pp. 504–509. Springer, Heidelberg (2008)
Warren Burhenne, L.J., Wood, S.A., D’Orsi, C.J., Feig, S.A., Kopans, D.B., O’Shaughnessy, K.F., Sickles, E.A., Tabar, L., Vyborny, C.J., Castellino, R.A.: Potential contribution of computer-aided detection to the sensitivity of screening mammography. Radiology 215(2), 554–562 (2000)
Skaane, P., Kshirsagar, A., Stapleton, S., Young, K., Castellino, R.A.: Effect of computer-aided detection on independent double reading of paired screen-film and full-field digital screening mammograms. Am. J. Roentgenol. 188(2), 377–384 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leichter, I., Lederman, R., Manevitch, A. (2012). Detecting Low-Conspicuity Mammographic Findings – The Real Added Value of CAD. In: Maidment, A.D.A., Bakic, P.R., Gavenonis, S. (eds) Breast Imaging. IWDM 2012. Lecture Notes in Computer Science, vol 7361. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31271-7_87
Download citation
DOI: https://doi.org/10.1007/978-3-642-31271-7_87
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31270-0
Online ISBN: 978-3-642-31271-7
eBook Packages: Computer ScienceComputer Science (R0)