Loading [MathJax]/extensions/MathMenu.js
Breast Lesion Classification Based on Shape Features | IEEE Conference Publication | IEEE Xplore

Breast Lesion Classification Based on Shape Features


Abstract:

In this study, it is aimed to classify breast lesions as benign/malignant by using breast magnetic resonance images taken from Sakarya University Training and Research Ho...Show More

Abstract:

In this study, it is aimed to classify breast lesions as benign/malignant by using breast magnetic resonance images taken from Sakarya University Training and Research Hospital with legal permission. For this purpose, at the first step breast lesion area is determined exactly by using region growing and Markov random field segmentation methods. Then, feature extraction process is performed by calculating fifteen shape features belonging to the lesion area. At the last step, lesion classification is carried out by utilizing k-nearest neighbor and support vector machines techniques. Radiologist's labeling results obtained according to the BIRADS assessment criteria are used to evaluate the classification performance.
Date of Conference: 24-26 April 2019
Date Added to IEEE Xplore: 22 August 2019
ISBN Information:
Print on Demand(PoD) ISSN: 2165-0608
Conference Location: Sivas, Turkey