Canonical polyadic decomposition for tissue type differentiation using multi-parametric MRI in high-grade gliomas
| Autor: | Nicolas Sauwen, Diana M. Sima, Uwe Himmelreich, S. Van Huffel, L. De Lathauwer, H. N. Bharath |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Multi parametric
SISTA medicine.diagnostic_test Magnetic resonance imaging medicine.disease Blind signal separation 030218 nuclear medicine & medical imaging Matrix decomposition 03 medical and health sciences 0302 clinical medicine Nuclear magnetic resonance Glioma medicine Signal processing algorithms Tissue type 030217 neurology & neurosurgery High-Grade Glioma Mathematics |
| Zdroj: | EUSIPCO |
| Popis: | © 2016 IEEE. In diagnosis and treatment planning of brain tumors, characterisation and localization of tissue plays an important role. Blind source separation techniques are generally employed to extract the tissue-specific profiles and its corresponding distribution from the multi-parametric MRI. A 3-dimensional tensor is constructed from in-vivo multiparametric MRI of high grade glioma patients. Constrained canonical polyadic decomposition (CPD) with common factor in mode-1 and mode-2 and l1 regularization on mode-3 is applied on the 3-dimensional multi-parametric tensor to characterize various tissue types. An initial in-vivo study shows that CPD has slightly better performance in identifying active tumor and the tumor core region in high-grade glioma patients compared to hierarchical non-negative matrix factorization. ispartof: pages:547-551 ispartof: Proc. of 24rd European Signal Processing Conference vol:2016-November pages:547-551 ispartof: EUSIPCO 2016 location:Budapest, Hungary date:28 Aug - 2 Sep 2016 status: published |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|