Discrimination of Malignant and Benign Breast Masses Using Computer-Aided Diagnosis from Dynamic Contrast-Enhanced Magnetic Resonance Imaging
- 3 June 2021
- journal article
- research article
- Published by Galenos Yayinevi in Medical Bulletin of Haseki
- Vol. 59 (3), 190-195
- https://doi.org/10.4274/haseki.galenos.2021.6819
Abstract
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 (ROls). 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.Keywords
This publication has 24 references indexed in Scilit:
- Survey on Image Segmentation TechniquesProcedia Computer Science, 2015
- Reliability Modeling and Life Estimation Using an Expectation Maximization Based Wiener Degradation Model for Momentum WheelsIEEE Transactions on Cybernetics, 2014
- Abbreviated Breast Magnetic Resonance Imaging (MRI): First Postcontrast Subtracted Images and Maximum-Intensity Projection—A Novel Approach to Breast Cancer Screening With MRIJournal of Clinical Oncology, 2014
- Machine learning and radiologyMedical Image Analysis, 2012
- Manifold Learning for Medical Image Registration, Segmentation, and ClassificationPublished by IGI Global ,2012
- Prospective Study of Breast Cancer Incidence in Women With a BRCA1 or BRCA2 Mutation Under Surveillance With and Without Magnetic Resonance ImagingJournal of Clinical Oncology, 2011
- Benefits of Screening MammographyJAMA, 2010
- A Fuzzy C-Means (FCM)-Based Approach for Computerized Segmentation of Breast Lesions in Dynamic Contrast-Enhanced MR Images1Academic Radiology, 2006
- Evaluation of radiological features for breast tumour classification in clinical screening with machine learning methodsArtificial Intelligence in Medicine, 2005
- Clinically and Mammographically Occult Breast Lesions on MR Images: Potential Effect of Computerized Assessment on Clinical ReadingRadiology, 2005