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

Haseki Tıp Bülteni

Ahmet Hasim Yurttakal¹  Hasan Erbay²  Seyhan Karacavus³  Turkan Ikizceli⁴ 

[1] Afyon Kocatepe University Faculty of Engineering, Department of Computer Engineering, Afyon, Turkey;Turkish Aeronautical Association University Faculty of Engineering, Department of Computer Engineering, Ankara, Turkey;University of Health Sciences Faculty of Medicine, Department of Nuclear Medicine, Kayseri, Turkey;University of Health Sciences Turkey, Istanbul Haseki Training and Research Hospital, Clinic of Radiology, Istanbul, Turkey;

关键词: breast lesions;    breast cancer;    magnetic resonance imaging;    computer-aided diagnosis;    segmentation;   

DOI  :  10.4274/haseki.galenos.2021.6819

来源: DOAJ

【 摘 要 】

Aim:To reduce operator dependency and achieve greater accuracy, the computer-aided diagnosis (CAD) systems are becoming a useful tool for detecting noninvasively and determining tissue characterization in medical images. We aimed to suggest a CAD system in discriminating between benign and malignant breast masses.Methods:The dataset was composed of 105 randomly breast magnetic resonance imaging (MRI) including biopsy-proven breast lesions (53 malignant, 52 benign). The expectation-maximization (EM) algorithm was used for image segmentation. 2D-discrete wavelet transform was applied to each region of interests (ROIs). After that, intensity-based statistical and texture matrix-based features were extracted from each of the 105 ROIs. Random Forest algorithm was used for feature selection. The final set of features, by random selection base, splatted into two sets as 80% training set (84 MRI) and 20% test set (21 MRI). Three classification algorithms are such that decision tree (DT, C4.5), naive bayes (NB), and linear discriminant analysis (LDA) were used. The accuracy rates of algorithms were compared.Results:C4.5 algorithm classified 20 patients correctly with a success rate of 95.24%. Only one patient was misclassified. The NB classified 19 patients correctly with a success rate of 90.48%. The LDA Algorithm classified 18 patients correctly with a success rate of 85.71%.Conclusion:The CAD equipped with the EM segmentation and C4.5 DT classification was successfully distinguished as benign and malignant breast tumor on MRI.

【 授权许可】

Unknown