Brain tumor segmentation in MR images using a sparse constrained level set algorithm

• Published in: Expert systems with applications Vol. 168; p. 114262
• Main Authors: Lei, Xiaoliang, Yu, Xiaosheng, Chi, Jianning, Wang, Ying, Zhang, Jingsi, Wu, Chengdong
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 15.04.2021; Elsevier BV
• Subjects: Algorithms; Brain; Brain cancer; Brain tumor; Constraint modelling; Image segmentation; Level set; Magnetic resonance imaging; Medical imaging; Sparse constraint; Tumors; Brain tumor; Image segmentation; Level set; Sparse constraint
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2020.114262

Brain tumor segmentation using Magnetic Resonance (MR) Imaging technology plays a significant role in computer-aided brain tumor diagnosis. However, when applying classic segmentation methods, limitations such as inhomogeneous intensity, complex physiological structure and blurred tissues boundaries in brain MR images usually lead to unsatisfactory results. To address these issues, this paper proposes an automatic sparse constrained level set method to realize the brain tumor segmentation in MR images. By studying brain tumor images, this method finds out common characteristics of brain tumors’ shape and constructs a sparse representation model. By considering this model as a prior constraint, an energy function based on level set method is constructed. In experiments, the proposed method can achieve an average accuracy of 96.20% for the MR images from the dataset Brats2017 and performs better than the others. With lower false positive rate and stronger robustness, the experimental results show that the proposed method can segment brain tumor from MR image accurately and stably. •Automatically locate brain tumors and generate initial contours in MR images.•Construct a sparse shape constraint and incorporate it into the energy function.•Improve the performance of level set method in segmenting complex brain tumor.