The successive projection algorithm as an initialization method for brain tumor segmentation using non-negative matrix factorization.

Autor: Sauwen N; KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Centre for Dynamical Systems, Signal Processing and Data Analytics, Leuven, Belgium.; imec, Leuven, Belgium., Acou M; Ghent University Hospital, Department of Radiology, Ghent, Belgium., Bharath HN; KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Centre for Dynamical Systems, Signal Processing and Data Analytics, Leuven, Belgium.; imec, Leuven, Belgium., Sima DM; KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Centre for Dynamical Systems, Signal Processing and Data Analytics, Leuven, Belgium.; imec, Leuven, Belgium.; Icometrix, R&D Department, Leuven, Belgium., Veraart J; University of Antwerp, iMinds Vision Lab, Department of Physics, Antwerp, Belgium., Maes F; KU Leuven, Department of Electrical Engineering (ESAT), PSI Centre for Processing Speech and Images, Leuven, Belgium., Himmelreich U; KU Leuven, Department of Imaging and Pathology, Biomedical MRI/MoSAIC, Leuven, Belgium., Achten E; Ghent University Hospital, Department of Radiology, Ghent, Belgium., Van Huffel S; KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Centre for Dynamical Systems, Signal Processing and Data Analytics, Leuven, Belgium.; imec, Leuven, Belgium.
Jazyk: angličtina
Zdroj: PloS one [PLoS One] 2017 Aug 28; Vol. 12 (8), pp. e0180268. Date of Electronic Publication: 2017 Aug 28 (Print Publication: 2017).
DOI: 10.1371/journal.pone.0180268
Abstrakt: Non-negative matrix factorization (NMF) has become a widely used tool for additive parts-based analysis in a wide range of applications. As NMF is a non-convex problem, the quality of the solution will depend on the initialization of the factor matrices. In this study, the successive projection algorithm (SPA) is proposed as an initialization method for NMF. SPA builds on convex geometry and allocates endmembers based on successive orthogonal subspace projections of the input data. SPA is a fast and reproducible method, and it aligns well with the assumptions made in near-separable NMF analyses. SPA was applied to multi-parametric magnetic resonance imaging (MRI) datasets for brain tumor segmentation using different NMF algorithms. Comparison with common initialization methods shows that SPA achieves similar segmentation quality and it is competitive in terms of convergence rate. Whereas SPA was previously applied as a direct endmember extraction tool, we have shown improved segmentation results when using SPA as an initialization method, as it allows further enhancement of the sources during the NMF iterative procedure.
Databáze: MEDLINE
Externí odkaz: