Title: Unsupervised and Semi-supervised Non-negative Matrix Factorization Methods for Brain Tumor Segmentation using Multi-parametric MRI Data
Other Titles: Ongesuperviseerde en semi-gesuperviseerde niet-negatieve matrix factorizatie methoden voor de segmentatie van hersentumoren op basis van multi-parametrische MRI data
Authors: Sauwen, Nicolas
Issue Date: 5-Dec-2016
Abstract: Gliomas represent about 80% of all malignant primary brain tumors. Despite recent advancements in glioma research, patient outcome remains poor. Magnetic resonance imaging (MRI) has become the imaging modality of choice in the management of brain tumor patients. Over the past decade, advanced MRI modalities, such as perfusion-weighted imaging, diffusion-weighted imaging and magnetic resonance spectroscopic imaging have gained interest in the clinical field, and their added value has been recognized. Tumor segmentation plays an important role in treatment planning as well as during follow-up. Manual segmentation by a clinical expert is currently the gold standard, but it is a tedious and time-consuming task. Clinical practice would benefit from accurate and automated volumetric delineation of the tumor and its sub-compartments.
Throughout this PhD, methods have been developed for automated segmentation and characterization of brain tumors. The proposed methods are based on an unsupervised learning technique called non-negative matrix factorization (NMF). NMF provides an additive parts-based representation of the input data, revealing the basic components which are present. Applied to the multi-parametric MR imaging data of a brain tumor patient, NMF is able to extract tissue-specific signatures as well as the relative proportions of the different tissue types in each voxel. Being an unsupervised method, NMF cannot benefit from an extensive training dataset to learn decision boundaries between tissue classes, but it is directly applicable to any multi-parametric MRI dataset of any individual patient.
Table of Contents: Abstract
List of Figures
List of Tables
1. Introduction
2. Non-negative matrix factorization and validation metrics
3. Multi-parametric MRI datasets and pre-processing
4. Hierarchical non-negative matrix factorization to characterize brain tumor heterogeneity using MP-MRI data
5.The successive projection algorithm as an initialization method for brain tumor segmentation using NMF
6. Comparison of unsupervised classification methods for brain tumor segmentation using MP-MRI data
7. Semi-automated brain tumor segmentation on MP-MRI data using regularized NMF
8. Application of semi-automated regularized NMF to the BRATS 2013 Leaderboard dataset
9. Conclusions and future perspectives
Appendix A: Validation scores individual UZ Leuven patients
Curriculum vitae
List of publications
Publication status: published
KU Leuven publication type: TH
Appears in Collections:Radiology
Electrical Engineering - miscellaneous
Biomedical MRI
ESAT - PSI, Processing Speech and Images
ESAT - STADIUS, Stadius Centre for Dynamical Systems, Signal Processing and Data Analytics

Files in This Item:
File Status SizeFormat
Thesis NSauwen final.pdf Published 21450KbAdobe PDFView/Open Request a copy

These files are only available to some KU Leuven Association staff members


All items in Lirias are protected by copyright, with all rights reserved.