Ensemble segmentation for GBM brain tumors on MR images using confidence‐based averaging

Huo, Jing; Okada, Kazunori; Rikxoort, Eva M. van; Kim, Hee Jin; Alger, Jeffry R.; Pope, Whitney B.; Goldin, Jonathan G.; Brown, Matthew S.

doi:10.1118/1.4817475

Cited by 13 publications

(7 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These modalities can be used for the localization of the different areas of the brain tumor. PI data [144,145] , DTI data [146,147] , and MRS data [148,149] have been used to segment brain tumor from normal tissues by the existence of machine learning methods. Along with the advance of studies in the area, brain tumor automatic segmentation technology has the potential to provide better prognostic information and optimize treatment options.…”

Section: Discussionmentioning

confidence: 99%

A survey of MRI-based brain tumor segmentation methods

Liu

Wang

et al. 2014

Tinshhua Sci. Technol.

288

View full text Add to dashboard Cite

Brain tumor segmentation aims to separate the different tumor tissues such as active cells, necrotic core, and edema from normal brain tissues of White Matter (WM), Gray Matter (GM), and Cerebrospinal Fluid (CSF). MRIbased brain tumor segmentation studies are attracting more and more attention in recent years due to non-invasive imaging and good soft tissue contrast of Magnetic Resonance Imaging (MRI) images. With the development of almost two decades, the innovative approaches applying computer-aided techniques for segmenting brain tumor are becoming more and more mature and coming closer to routine clinical applications. The purpose of this paper is to provide a comprehensive overview for MRI-based brain tumor segmentation methods. Firstly, a brief introduction to brain tumors and imaging modalities of brain tumors is given. Then, the preprocessing operations and the state of the art methods of MRI-based brain tumor segmentation are introduced. Moreover, the evaluation and validation of the results of MRI-based brain tumor segmentation are discussed. Finally, an objective assessment is presented and future developments and trends are addressed for MRI-based brain tumor segmentation methods.

show abstract

Section: Discussionmentioning

confidence: 99%

A survey of MRI-based brain tumor segmentation methods

Liu

Wang

et al. 2014

Tinshhua Sci. Technol.

288

View full text Add to dashboard Cite

show abstract

“…However, having multiple parameters complicates the extraction of diagnostic information across the images on a voxel basis, and necessitates the use of automatic or semi-automatic segmentation methods [12][13][14][15][16]. Automatic segmentation can be performed based on various imaging parameters extracted from the raw data or in the temporal domain; they can be categorized into supervised or unsupervised algorithms, and can either be performed at the group-or at the subject-level.…”

Section: Introductionmentioning

confidence: 99%

Classification of tumor area using combined DCE and DSC MRI in patients with glioblastoma

et al. 2014

View full text Add to dashboard Cite

This study proposes an automatic method for identification and quantification of different tissue components: the non-enhanced infiltrative tumor, vasogenic edema and enhanced tumor areas, at the subject level, in patients with glioblastoma (GB) based on dynamic contrast enhancement (DCE) and dynamic susceptibility contrast (DSC) MRI. Nineteen MR data sets, obtained from 12 patients with GB, were included. Seven patients were scanned before and 8 weeks following bevacizumab initiation. Segmentation of the tumor area was performed based on the temporal data of DCE and DSC at the group-level using k-means algorithm, and further at the subject-level using support vector machines algorithm. The obtained components were associated to different tissues types based on their temporal characteristics, calculated perfusion and permeability values and MR-spectroscopy. The method enabled the segmentation of the tumor area into the enhancing permeable component; the non-enhancing hypoperfused component, associated with vasogenic edema; and the non-enhancing hyperperfused component, associated with infiltrative tumor. Good agreement was obtained between the group-level, unsupervised and subject-level, supervised classification results, with significant correlation (r = 0.93, p < 0.001) and average symmetric root-mean-square surface distance of 2.5 ± 5.1 mm. Longitudinal changes in the volumes of the three components were assessed alongside therapy. Tumor area segmentation using DCE and DSC can be used to differentiate between vasogenic edema and infiltrative tumors in patients with GB, which is of major clinical importance in therapy response assessment.

show abstract

“…Damangir et al and Kasiri et al [15,19] used SVM method for human brain MRI image segmentation. Ensemble methods are the other category of machine learning based methods which are used for tumor and brain tissue segmentation [15,20,21].…”

Section: Introductionmentioning

confidence: 99%

Supervised segmentation of MRI brain images using combination of multiple classifiers

Ahmadvand

Sharififar

Daliri

2015

Australas Phys Eng Sci Med

View full text Add to dashboard Cite

Segmentation of different tissues is one of the initial and most critical tasks in different aspects of medical image processing. Manual segmentation of brain images resulted from magnetic resonance imaging is time consuming, so automatic image segmentation is widely used in this area. Ensemble based algorithms are very reliable and generalized methods for classification. In this paper, a supervised method named dynamic classifier selection-dynamic local training local tanimoto index, which is a member of combination of multiple classifiers (CMCs) methods is proposed. The proposed method uses dynamic local training sets instead of a full statics one and also it change the classifier rank criterion properly for brain tissue classification. Selection policy for combining the different decisions is implemented here and the K-nearest neighbor algorithm is used to find the best local classifier. Experimental results show that the proposed method can classify the real datasets of the internet brain segmentation repository better than all single classifiers in ensemble and produces significantly improvement on other CMCs methods.

show abstract

Ensemble segmentation for GBM brain tumors on MR images using confidence‐based averaging

Abstract: The results showed that the CMA ensemble result statistically approximates the best segmentation result of all the base methods for each case.

Cited by 13 publications

References 47 publications

A survey of MRI-based brain tumor segmentation methods

A survey of MRI-based brain tumor segmentation methods

Classification of tumor area using combined DCE and DSC MRI in patients with glioblastoma

Supervised segmentation of MRI brain images using combination of multiple classifiers

Contact Info

Product

Resources

About