Hierarchical non‐negative matrix factorization (hNMF): a tissue pattern differentiation method for glioblastoma multiforme diagnosis using MRSI. (13th September 2012)

• Record Type: Journal Article
• Authors: Li, Yuqian; Sima, Diana M.; Cauter, Sofie Van; Croitor Sava, Anca R.; Himmelreich, Uwe; Pi, Yiming; Van Huffel, Sabine
• Is Part Of: NMR in biomedicine. Volume 26:Number 3(2013:Mar.)
• Page Start: 307
• Page End: 319
• Publication Date: 2012-09-13
• Subjects: hierarchical non‐negative matrix factorization (hNMF) -- non‐negative matrix factorization (NMF) -- blind source separation (BSS) -- MRSI -- glioblastoma multiforme (GBM); Nuclear magnetic resonance -- Periodicals; Magnetic Resonance Spectroscopy -- Periodicals; 574
• DOI: 10.1002/nbm.2850
• Languages: English
• ISSNs: 0952-3480

Abstract

Abstract : MRSI has shown potential in the diagnosis and prognosis of glioblastoma multiforme (GBM) brain tumors, but its use is limited by difficult data interpretation. When the analyzed MRSI data present more than two tissue patterns, conventional non‐negative matrix factorization (NMF) implementation may lead to a non‐robust estimation. The aim of this article is to introduce an effective approach for the differentiation of GBM tissue patterns using MRSI data. A hierarchical non‐negative matrix factorization (hNMF) method that can blindly separate the most important spectral sources in short‐TE 1 H MRSI data is proposed. This algorithm consists of several levels of NMF, where only two tissue patterns are computed at each level. The method is demonstrated on both simulated and in vivo short‐ TE 1 H MRSI data in patients with GBM. For the in vivo study, the accuracy of the recovered spectral sources was validated using expert knowledge. Results show that hNMF is able to accurately estimate the three tissue patterns present in the tumoral and peritumoral area of a GBM, i.e. normal, tumor and necrosis, thus providing additional useful information that can help in the diagnosis of GBM. Moreover, the hNMF results can be displayed as easily interpretable maps showing the contribution of each tissue pattern to each voxel. Copyright © 2012 John Wiley & Sons, Ltd. Abstract : Because of the heterogeneity of glioblastoma multiforme (GBM), the tumoral region can consist of several tissue patterns. The proposed hierarchical method firstly differentiates the MRSI signals into normal and abnormal sources. Then, tumor and necrosis are separated from the abnormal signals using an optimized threshold. The significance of this method involves the accurate recovery of the three most important tissue‐specific sources for patients with GBM. Simultaneous estimations of the corresponding spatial distributions could provide additional guidance for surgery.