c o m p u t e r m e t h o d s a n d p r o g r a m s i n b i o m e d i c i n e 1 2 3 ( 2 0 1 6 ) 43–53 jo ur nal ho me p ag e: www.intl.elsevierhealt h.com/journals/cmpb A novel breast ultrasound image segmentation algorithm based on neutrosophic similarity score and level set Yanhui Guo a,* , Abdulkadir S ¸ engür b , Jia-Wei Tian c a Department of Computer Science, University of Illinois at Springfield, Springfield, IL, USA b Department of Electric and Electronics Engineering, Technology Faculty, Firat University, Elazig, Turkey c Department of Ultrasound, Second Affiliated Hospital of Harbin Medical, Harbin, Heilongjiang, China a r t i c l e i n f o Article history: Received 23 April 2015 Received in revised form 2 September 2015 Accepted 8 September 2015 Keywords: Breast ultrasound Image segmentation Neutrosophic set Similarity score Level set a b s t r a c t Breast ultrasound (BUS) image segmentation is a challenging task due to the speckle noise, poor quality of the ultrasound images and size and location of the breast lesions. In this paper, we propose a new BUS image segmentation algorithm based on neutrosophic sim- ilarity score (NSS) and level set algorithm. At first, the input BUS image is transferred to the NS domain via three membership subsets T, I and F, and then, a similarity score NSS is defined and employed to measure the belonging degree to the true tumor region. Finally, the level set method is used to segment the tumor from the background tissue region in the NSS image. Experiments have been conducted on a variety of clinical BUS images. Several measurements are used to evaluate and compare the proposed method’s performance. The experimental results demonstrate that the proposed method is able to segment the BUS images effectively and accurately. © 2015 Elsevier Ireland Ltd. All rights reserved. 1. Introduction According to the statistics, breast cancer is one of the most common cancers among women and 232,670 new cases of invasive breast cancer were diagnosed among women in the US during 2014 [1], and an estimated 40,430 breast cancer deaths were expected in 2014 in US [2]. In statistics, breast cancer is indicated as the fifth most common causes of can- cer death. However, these deaths can be reduced if cases are detected and treated early [2]. Breast ultrasound (BUS) is known to be a major imaging modality due to its low cost, real time and dynamical imaging, and without ionizing radiation [3]. BUS has also proved to be a suitable tool for large-scale ∗ Corresponding author. Tel.: +1 4352275882. E-mail addresses: yanhui.guo@aggiusu.edu, yguo56@uis.edu (Y. Guo). screening addition to mammography in early detection of breast lesions [3]. However, clinical experience and expert knowledge are important factors to achieve accurate and fast diagnosis using BUS [3]. In other words, highly skilled physi- cians and radiologists are needed for interpretation of the BUS images. In the last decades, several decision support systems have been proposed for helping the physicians in order to inter- pret the BUS images [4]. Generally these systems are using image processing and pattern recognition algorithms. Espe- cially, image segmentation is vital to localize the lesions in these systems. However, speckle noise, poor quality and size and location of the breast lesions make this crucial step still challenging and difficult [3]. Up to now, a great number of http://dx.doi.org/10.1016/j.cmpb.2015.09.007 0169-2607/© 2015 Elsevier Ireland Ltd. All rights reserved.