A COMPARATIVE STUDY ON SEGMENTATION AND CLASSIFICATION IN BREAST MRI IMAGING


Yurttakal A. H. , ERBAY H., Ikizceli T., Karacavus S., ÇINARER G.

IIOAB JOURNAL, vol.9, no.5, pp.23-33, 2018 (Journal Indexed in ESCI) identifier

  • Publication Type: Article / Article
  • Volume: 9 Issue: 5
  • Publication Date: 2018
  • Title of Journal : IIOAB JOURNAL
  • Page Numbers: pp.23-33

Abstract

Background: Breast cancer is the type of cancer that develops from cells in the breast tissue. The breast cancer is leading cancer in women. One in every eight to nine women has breast cancer at some point during their lifetime. Computer-Aided Diagnosis (CAD) Technology is getting more important to assist radiologists not only to detect breast cancer tumor but also to interpret lesioned regions. The CAD, as a second reader in the clinic, improves the classification of malignant and benign lesions. On the other hand, Magnetic Resonance Imaging (MRI) is a highly recommended test for detecting and monitoring breast cancer tumors and interpreting lesioned regions since it has an excellent capability for soft tissue imaging. In MRI image analysis, the segmentation images are important objective because accurate measurement of the delineation of the regions of interest (ROI) is critical for the breast cancer diagnosis and treatment. Herein, by using MRI scans, we propose a semi-automated CAD system prototype to assist radiologists in detecting breast cancer tumors and interpreting lesioned regions. The prototype, first, pre-processes the raw selected suspicious region to reduce the noises and to reveal the structure. Later, using Expectation Maximization (EM), the prototype segments the pre-processed region. After that, we use the Discrete Wavelet Transform (DWT) for providing efficient multi-resolution sub and decomposition of signals. Then Random Forest Algorithm is used for feature selection. Finally, Naive Bayes, Linear Discriminant Analysis and C4.5 Decision Tree Algorithms are used to classify the features of the ROI in the diagnosis analysis. We tested the prototype CAD on 105 patients, among them, 53 are benign and 52 malign. 80% of the images are allocated for training and 20% of images reserved for testing. The CAD classified 20 patients correctly in case of 5 fold cross-validation. Only one patient is misclassified. The computer-aided diagnosis system with the C4.5 has accuracy 95.24%. Furthermore, C4.5 classifies the breast cancer tumors better than Naive Bayes and Linear Discriminant Analysis. We tested the prototype CAD on 105 patients, among them, 53 are benign and 52 malign. The computer-aided diagnosis system with the C4.5 has accuracy 95.24%. Furthermore, C4.5 classifies the breast cancer tumors better than Naive Bayes and Linear Discriminant Analysis.