Automatic glioma segmentation based on adaptive superpixel
- PDF / 13,841,163 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 15 Downloads / 223 Views
RESEARCH ARTICLE
Open Access
Automatic glioma segmentation based on adaptive superpixel Yaping Wu1, Zhe Zhao2, Weiguo Wu1*, Yusong Lin2 and Meiyun Wang3
Abstract Background: The automatic glioma segmentation is of great significance for clinical practice. This study aims to propose an automatic method based on superpixel for glioma segmentation from the T2 weighted Magnetic Resonance Imaging. Methods: The proposed method mainly includes three steps. First, we propose an adaptive superpixel generation algorithm based on simple linear iterative clustering version with 0 parameter (ASLIC0). This algorithm can acquire a superpixel image with fewer superpixels and better fit the boundary of region of interest (ROI) by automatically selecting the optimal number of superpixels. Second, we compose a training set by calculating the statistical, texture, curvature and fractal features for each superpixel. Third, Support Vector Machine (SVM) is used to train classification model based on the features of the second step. Results: The experimental results on Multimodal Brain Tumor Image Segmentation Benchmark 2017 (BraTS2017) show that the proposed method has good segmentation performance. The average Dice, Hausdorff distance, sensitivity, and specificity for the segmented tumor against the ground truth are 0.8492, 3.4697 pixels, 81.47, and 99.64%, respectively. The proposed method shows good stability on high- and low-grade glioma samples. Comparative experimental results show that the proposed method has superior performance. Conclusions: This provides a close match to expert delineation across all grades of glioma, leading to a fast and reproducible method of glioma segmentation. Keywords: Glioma segmentation, Superpixel, MRI, Medical image processing, Machine learning
Background Glioma is a prevalent brain disease with high malignancy, mortality, and disability [1, 2]. Magnetic resonance imaging (MRI) is widely used in the clinical diagnosis of glioma, can clearly reflect the anatomical structure of human soft tissue, and can accurately display the location, size and histological characteristics of lesions. The segmentation of glioma lesions are the key steps for computer-aided diagnosis, surgery, radiotherapy, and chemotherapy planning of brain glioma. Gliomas show infiltrative growth with lack of clear boundary and fixed growth pattern. Complex pathological changes, such as hemorrhage, necrosis, and edema, are found inside tumors. Gliomas show complex changes in brightness and texture on MRI images because of the * Correspondence: [email protected] 1 School of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, Shaanxi, China Full list of author information is available at the end of the article
complex pathological changes. Different tissues may have similar gray values, which present challenges to the accurate, repeatable, and stable segmentation of gliomas. In clinical application, radiologists mainly perform manual segmentation, which is subjective, has heavy workload, and difficu
Data Loading...
