Abstract
We have developed a multiscale algorithm for segmenting breast calcifications from high-resolution specimen radiographs. The algorithm was evaluated using 152 mammographic regions of interest digitized at a 15-μm spatial resolution. The true-positive detection rate was approximately 97.4% with 0.67 false-positives per image, and the segmentation error of individual calcification particles was approximately 5%. The performance of the algorithm is highly satisfactory.
Similar content being viewed by others
References
Yoshida H, Doi K, Nishikawa RM, et al: An improved computer-assisted diagnostic scheme using wavelet transform for detecting clustered microcalcifications in digital mammograms. Acad Radiol 3:621–627, 1996
Karssemeijer N: Adaptive noise equalization and recognition of microcalcification clusters in mammograms. Int J Pattern Recogn Artif Intell 7:1357–1376, 1993
Veldkamp WJH, Karssemeijer N: Improved correction for signal dependent noise applied to automatic detection of microcalcifications, in Karssemeijer N, Thijssen M, Hendriks J, et al (eds): Digital Mammography ’98. Nijmegen, Netherlands, Kluwer Academic, 1998, pp 169–176
Dengler J, Behrens S, Desaga JF: Segmentation of microcalcifications in mammograms. IEEE Trans Med Imaging 12:634–642, 1993
Näppi J: Computer-Assisted Diagnosis of Breast Calcifications. PhD thesis manuscript. Turku Centre for Computer Science, University of Turku, Turku, Finland, 2000
Jain AK: Fundamentals of Digital Image Processing. USA, Prentice Hall International, 1989
Shen L, Rangayyan RM, Desautels JEL: Application of shape analysis to mammographic calcifications. IEEE Trans Med Imaging 13:263–274, 1994
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by research grants from Turku University Foundation and Yrjö Jahnsson Foundation. The Finnish Academy provided partial support.
Rights and permissions
About this article
Cite this article
Näppi, J., Dean, P.B. A multiscale algorithm for segmenting calcifications from high-resolution mammographic specimen radiographs. J Digit Imaging 13 (Suppl 1), 130–132 (2000). https://doi.org/10.1007/BF03167643
Issue Date:
DOI: https://doi.org/10.1007/BF03167643