Ensemble segmentation for GBM brain tumors on MR images using confidence-based averaging
- PMID: 24007185
- DOI: 10.1118/1.4817475
Ensemble segmentation for GBM brain tumors on MR images using confidence-based averaging
Abstract
Purpose: Ensemble segmentation methods combine the segmentation results of individual methods into a final one, with the goal of achieving greater robustness and accuracy. The goal of this study was to develop an ensemble segmentation framework for glioblastoma multiforme tumors on single-channel T1w postcontrast magnetic resonance images.
Methods: Three base methods were evaluated in the framework: fuzzy connectedness, GrowCut, and voxel classification using support vector machine. A confidence map averaging (CMA) method was used as the ensemble rule.
Results: The performance is evaluated on a comprehensive dataset of 46 cases including different tumor appearances. The accuracy of the segmentation result was evaluated using the F1-measure between the semiautomated segmentation result and the ground truth.
Conclusions: The results showed that the CMA ensemble result statistically approximates the best segmentation result of all the base methods for each case.
Similar articles
-
A review on brain tumor segmentation of MRI images.Magn Reson Imaging. 2019 Sep;61:247-259. doi: 10.1016/j.mri.2019.05.043. Epub 2019 Jun 11. Magn Reson Imaging. 2019. PMID: 31200024 Review.
-
Radiological features of infantile glioblastoma and desmoplastic infantile tumors: British Columbia's Children's Hospital experience.J Neurosurg Pediatr. 2015 Aug;16(2):119-25. doi: 10.3171/2014.10.PEDS13634. Epub 2015 May 8. J Neurosurg Pediatr. 2015. PMID: 25955808 Review.
-
A fully automatic extraction of magnetic resonance image features in glioblastoma patients.Med Phys. 2014 Apr;41(4):042301. doi: 10.1118/1.4866218. Med Phys. 2014. PMID: 24694151
-
Robust texture features for response monitoring of glioblastoma multiforme on T1-weighted and T2-FLAIR MR images: a preliminary investigation in terms of identification and segmentation.Med Phys. 2010 Apr;37(4):1722-36. doi: 10.1118/1.3357289. Med Phys. 2010. PMID: 20443493
-
Application of fuzzy c-means segmentation technique for tissue differentiation in MR images of a hemorrhagic glioblastoma multiforme.Magn Reson Imaging. 1995;13(2):277-90. doi: 10.1016/0730-725x(94)00093-i. Magn Reson Imaging. 1995. PMID: 7739370
Cited by
-
An Automatic Segmentation Method for Lung Tumor Based on Improved Region Growing Algorithm.Diagnostics (Basel). 2022 Nov 28;12(12):2971. doi: 10.3390/diagnostics12122971. Diagnostics (Basel). 2022. PMID: 36552978 Free PMC article.
-
Lightweight Learning-Based Automatic Segmentation of Subretinal Blebs on Microscope-Integrated Optical Coherence Tomography Images.Am J Ophthalmol. 2021 Jan;221:154-168. doi: 10.1016/j.ajo.2020.07.020. Epub 2020 Jul 21. Am J Ophthalmol. 2021. PMID: 32707207 Free PMC article.
-
Within-brain classification for brain tumor segmentation.Int J Comput Assist Radiol Surg. 2016 May;11(5):777-88. doi: 10.1007/s11548-015-1311-1. Epub 2015 Nov 3. Int J Comput Assist Radiol Surg. 2016. PMID: 26530300
-
Classification of tumor area using combined DCE and DSC MRI in patients with glioblastoma.J Neurooncol. 2015 Jan;121(2):349-57. doi: 10.1007/s11060-014-1639-3. Epub 2014 Nov 5. J Neurooncol. 2015. PMID: 25370705
-
Automated Delineation of Lung Tumors from CT Images Using a Single Click Ensemble Segmentation Approach.Pattern Recognit. 2013 Mar 1;46(3):692-702. doi: 10.1016/j.patcog.2012.10.005. Pattern Recognit. 2013. PMID: 23459617 Free PMC article.
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical