Multimedia Tools and Applications https://doi.org/10.1007/s11042-019-7185-4 Extraction of spiculated parts of mammogram tumors to improve accuracy of classification H. Pezeshki 1 · M. Rastgarpour 2 · A. Sharifi 1 · S. Yazdani 3 Received: 4 June 2018 / Revised: 20 December 2018 / Accepted: 6 January 2019 / © Springer Science+Business Media, LLC, part of Springer Nature 2019 Abstract Spiculated parts of masses are significant features to classify tumors in digital mammog- raphy; however, segmentation, which is used to extract the shape and contour of a tumor, eliminates them. To address this problem, the current study proposes a novel algorithm for extraction of the spiculated pixels of a tumor that are of similar intensity along a line. It first applies the sums of the differences between the central pixel and neighboring pixels in different symmetric orthogonal directions. The minimum difference between two sym- metric orthogonal directions specifies the similarity of pixels in one direction as denoting a spiculated part of the mass. These parts then are added to the segmented image to enhance the shape of tumor. The features of the tumor are extracted from the final segmented image to allow its classification as benign or malignant. Simulation results showed that the accu- racy and the area under the ROC curve of the proposed method for mini-MIAS and DDSM databases were 91.37% and 93.22% and 0.9776 and 0.9752, respectively. This confirms the effectiveness of the proposed algorithm for extraction of the spiculated parts of a malignant tumor with the aim of increasing the classification accuracy. Keywords Mammographic mass classification · Breast cancer · Extraction of spiculated parts · Segmentation · Feature extraction  M. Rastgarpour m.rastgarpour@iau-saveh.ac.ir H. Pezeshki hamed.pezeshki@srbiau.ac.ir A. Sharifi a.sharifi@srbiau.ac.ir S. Yazdani s yazdani@iau-tnb.ac.ir 1 Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran 2 Department of Computer Engineering, Faculty of Engineering, Saveh Branch, Islamic Azad University, Saveh, Iran 3 Department of Computer Engineering, North Tehran Branch, Islamic Azad University, Tehran, Iran