Volume 3, Issue 4 (Multidisciplinary Cancer Investigation 2019)                   Multidiscip Cancer Investig 2019, 3(4): 13-24 | Back to browse issues page


XML Print


1- Department of Biomedical Engineering, Dezful Branch, Islamic Azad University, Dezful, Iran , Naser.safdarian@yahoo.com
2- Department of Biomedical Engineering, Dezful Branch, Islamic Azad University, Dezful, Iran
Abstract:   (4058 Views)
Introduction: In this paper, a method is presented to classify the breast cancer masses according to new geometric features.
Methods: After obtaining digital breast mammogram images from the digital database for screening mammography (DDSM), image preprocessing was performed. Then, by using image processing methods, an algorithm was developed for automatic extracting of masses from other normal parts of the breast image. In this study, 19 final different features of each image were extracted to generate the feature vector for classifier input. The proposed method not only determined the boundary of masses but also classified the type of masses such as benign and malignant ones. The neural network classification methods such as the radial basis function (RBF), probabilistic neural network (PNN), and multi-layer perceptron (MLP) as well as  the Takagi-Sugeno-Kang (TSK) fuzzy classification,  the  binary  statistic  classifier,  and  the  k-nearest  neighbors  (KNN) clustering algorithm were used for the final decision of mass class.
Results: The best results of the proposed method for accuracy, sensitivity, and specificity metrics were obtained 97%±4.36, 100%±0 and 96%±5.81, respectively for support vector machine (SVM) classifier.
Conclusions: By comparing the results of the proposed method with the results of the other previous methods, the efficiency of the proposed algorithm was reported.
Full-Text [PDF 651 kb]   (5008 Downloads)    
Select article type: Original/Research Article |
Received: 2019/08/8 | Accepted: 2019/10/16 | ePublished: 2019/10/1

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.