A reliable ensemble-based classification framework for glioma brain tumor segmentation
- PDF / 2,281,688 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 1 Downloads / 219 Views
ORIGINAL PAPER
A reliable ensemble-based classification framework for glioma brain tumor segmentation Zeynab Barzegar1
· Mansour Jamzad1
Received: 16 October 2019 / Revised: 22 March 2020 / Accepted: 23 April 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Glioma is one of the most frequent primary brain tumors in adults that arise from glial cells. Automatic and accurate segmentation of glioma is critical for detecting all parts of tumor and its surrounding tissues in cancer detection and surgical planning. In this paper, we present a reliable classification framework for detection and segmentation of abnormal tissues including brain glioma tumor portions such as edemas and tumor core. This framework learns weighted features extracted from the 3D cubic neighborhoods regarding to gray-level differences that indicate the spatial relationships among voxels. In addition to intensity values in each slice, we consider sets of three consecutive slices to extract information from 3D neighbors. Classification procedure is defined based on combination of support vector machines regarding to an ensemble learning method. In order to regularize and improve the output of the classifier framework, we design a post-process procedure based on statistical concepts. The proposed framework is trained and tested with BRATS datasets, and comparative analysis is implemented. Experimental results indicate competitive performance compared to the state-of-the-art methods. The achieved accuracy is characterized by the overall mean Dice index of 88%. Keywords Multimodal brain MRI · Glioma brain tumor · Segmentation · 3D neighborhood features · Gray-level difference · Ensemble learning
1 Introduction Brain tumor is the abnormal growth of cells inside brain. One of the most common malignant primary brain tumors in adults is known as glioma. It develops from the star-shaped glial cells that support nerve cells [1]. This kind of tumor can be classified into four grades; grades 1 and 2 are known as low-grade glioma tumors (LGGs) and grades 3 and 4 are the high-grade glioma tumors (HGGs). Brain tumor segmentation from multimodal magnetic resonance images (MRI) is one of the most valuable planning factors in surgery and radiotherapy. In many cases, considering the nature, shape, appearance and location of brain tumors, using one MRI sequence is not sufficient for segmenting the tumor and its subregions. Therefore, various MRI sequences including T1 weighted, T1 weighted with
B
Zeynab Barzegar [email protected] Mansour Jamzad [email protected]
1
Sharif University of Technology, Tehran, Iran
contrast enhancement (T1C ), T2 weighted and T2 weighted with fluid-attenuated inversion recovery (T2Flair ) are necessary for better results [2]. Regarding to segmentation challenges, numerous algorithms have been developed to perform brain tumor detection and segmentation [2,3]. Low-level operations, such as thresholding, edge detection and morphological techniques, are fast, and their performance specifically depends on
Data Loading...
