This paper presents a new method for automatic detection of clustered micro calcifications (both malignant and benign) in digitized mammograms. Compared to previous works, the innovation here is that the processing is performed by labeling the texture regions in the original image. This new method uses the labeling the textures of the mammographic images on the basis of UIQI (universal quality index). Once labeling is performed, mammogram is segmented into various regions and further thresholds are used to separate the clustered micro calcifications. By comparing our results with those found in the literature, we proved that the method enormously reduces the computing time as UIQI utilizes simple statistical features like mean, variance and standard deviations only. In this paper, an automatic segmentation and classification of massive lesions in mammographic images is evaluated on Mini-MIAS database consisting 320 digitalized mammograms. Furthermore, classification rates enhancements were also revealed by testing our method compared to existing methods. © 2011 Springer-Verlag.
CITATION STYLE
Chandra Murty, P. S. R., Sudheer, T., & Sreenivasa Reddy, E. (2011). Segmentation of micro calcification clusters in digital mammograms using UIQI. In Communications in Computer and Information Science (Vol. 205 CCIS, pp. 165–172). https://doi.org/10.1007/978-3-642-24055-3_17
Mendeley helps you to discover research relevant for your work.