Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6920351 | Computerized Medical Imaging and Graphics | 2013 | 10 Pages |
Abstract
Brain tumor segmentation is a clinical requirement for brain tumor diagnosis and radiotherapy planning. Automating this process is a challenging task due to the high diversity in appearance of tumor tissue among different patients and the ambiguous boundaries of lesions. In this paper, we propose a method to construct a graph by learning the population- and patient-specific feature sets of multimodal magnetic resonance (MR) images and by utilizing the graph-cut to achieve a final segmentation. The probabilities of each pixel that belongs to the foreground (tumor) and the background are estimated by global and custom classifiers that are trained through learning population- and patient-specific feature sets, respectively. The proposed method is evaluated using 23 glioma image sequences, and the segmentation results are compared with other approaches. The encouraging evaluation results obtained, i.e., DSC (84.5%), Jaccard (74.1%), sensitivity (87.2%), and specificity (83.1%), show that the proposed method can effectively make use of both population- and patient-specific information.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science Applications
Authors
Jun Jiang, Yao Wu, Meiyan Huang, Wei Yang, Wufan Chen, Qianjin Feng,