Improved active contour model for multi-phase MR image segmentation and bias field correction
Yunyun Yang, Wenjing Jia, Dongcai Tian · 2019
Magnetic resonance imaging (MRI) has been applied in the imaging of all tissues of human body. It is an important method for doctors to analyze the cause of diseases. In particular, the accurate segmentation of MR images is significant for doctors to diagnose the etiology. However, due to the limitation of the MRI equipment and technology, magnetic resonance (MR) images always have the intensity inhomogeneity and fuzzy edges, which makes the MR image segmentation more difficult. In this paper, the authors propose an improved multi-phase active contour model based on the clustering method, which can accurately segment the multiple tissues and correct the bias field of MR images at the same time. The authors give the multi-phase energy functional and minimize it by the split Bregman method, and experimental results show that the proposed model is more accurate and efficient.