A novel method for accurate detection of regions of interest (ROIs) that contain circumscribed lesions in X-rays mammograms based on bilateral subtraction is presented. Implementing this method requires left and right breast images alignment using a cross-correlation criterion followed by a windowing analysis in mammogram pairs. Furthermore, a set of qualification criteria is employed to filter these regions, retaining the most suspicious for which a Radial-Basis Function Neural Network makes the final decision marking them as ROIs that contain abnormal tissue. Extensive experiments have shown that the proposed method detects the location of the circumscribed lesions with accuracy of 95.8% in the MIAS database.
CITATION STYLE
Christoyianni, I., Constantinou, E., & Dermatas, E. (2004). Automatic detection of abnormal tissue in bilateral mammograms using neural networks. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3025, pp. 267–275). Springer Verlag. https://doi.org/10.1007/978-3-540-24674-9_28
Mendeley helps you to discover research relevant for your work.