Discrimination of Malignant and Benign Breast Masses Using Computer-Aided Diagnosis from Dynamic Contrast-Enhanced Magnetic Resonance Imaging

Abstract

Aim: To reduce operator dependency and achieve greater accuracy, the computer-aided diagnosis (CAD) systems are becoming auseful tool for detecting noninvasively and determining tissue characterization in medical images. We aimed to suggest a CAD systemin discriminating between benign and malignant breast masses.Methods: The dataset was composed of 105 randomly breast magnetic resonance imaging (MRI) including biopsy-proven breastlesions (53 malignant, 52 benign). The expectation-maximization (EM) algorithm was used for image segmentation. 2D-discrete wavelettransform was applied to each region of interests (ROIs). After that, intensity-based statistical and texture matrix-based features wereextracted from each of the 105 ROIs. Random Forest algorithm was used for feature selection. The final set of features, by randomselection base, splatted into two sets as 80% training set (84 MRI) and 20% test set (21 MRI). Three classification algorithms are suchthat decision tree (DT, C4.5), naive bayes (NB), and linear discriminant analysis (LDA) were used. The accuracy rates of algorithms werecompared.Results: C4.5 algorithm classified 20 patients correctly with a success rate of 95.24%. Only one patient was misclassified. The NBclassified 19 patients correctly with a success rate of 90.48%. The LDA Algorithm classified 18 patients correctly with a success rate of85.71%.Conclusion: The CAD equipped with the EM segmentation and C4.5 DT classification was successfully distinguished as benign andmalignant breast tumor on MRI.