Profile
International Journal of Computer & Software Engineering Volume 2 (2017), Article ID 2:IJCSE-119, 8 pages
https://doi.org/10.15344/2456-4451/2017/119
Research Article
3D Tumor Segmentation in Breast MRIs using 3D Modified Active Contour Method

Sheng-Chih Yang* and Che-Jui Hsu

Department of Computer Science and Information Engineering, National Chin Yi University of Technology, Taichung 41170, Taiwan
Dr. Sheng-Chih Yang, Department of Computer Science and Information Engineering, National Chin Yi University of Technology, Taichung 41170, Taiwan; E-mail: scyang@ncut.edu.tw
05 July 2017; 21 October 2017; 23 October 2017
Yang SC, Hsu CJ (2017) 3D Tumor Segmentation in Breast MRIs using 3D Modified Active Contour Method. Int J Comput Softw Eng 2: 119. doi: https://doi.org/10.15344/2456-4451/2017/119
This work was supported by the Ministry of Science and Technology, Taiwan, under Grant No. MOST 103-2221-E-167-025 and NSC 101- 2221-E-167-036.

Abstract

Medical image segmentation is an important aided technique for medical diagnosis. In the past, some researchers have proved effectiveness on two-dimensional (2D) image segmentation; but the achievements of three-dimensional (3D) image segmentation are still unsatisfactory and challenging. This paper presents a 3D Modified Active Contour Method (3D-MACM) that is aimed at breast tumor segmentation in 3D magnetic resonance images (MRI). It acquires an accurate 3D tumor segmented model in order to provide physicians with 3D function such as position, volume, shape characteristics, distribution, etc. In the development process of proposed method, the traditional 2D technique must first evolve into 3D technique and then modify the smoothing method to facilitate the overall operation of the stacked MRIs, so it is called 3D modified ACM. To assess the accuracy of 3D-MACM, we have conducted experiments on breast MRI and simulated cases and have compared with the traditional active contour method and level set method. The results show that not only is the method developed in this paper more accurate than traditional methods, it also has an accuracy greater than 99% and a false alarm rate less than 0.8%, according to the standard model.