MRSI data unmixing using spatial and spectral priors in transformed domains

A. Laruelo, L. Chaari, S. Ken, J.-Y. Tourneret, H. Batatia, A. Laprie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In high-grade gliomas, the tumor boundaries and the degree of infiltration are difficult to define due to their heterogeneous composition and diffuse growth pattern. Magnetic Resonance Spectroscopic Imaging (MRSI) is a non-invasive technique able to provide information on brain tumor biology not available from conventional anatomical imaging. In this paper we propose a blind source separation (BSS) algorithm for brain tissue classification and visualization of tumor spread using MRSI data. The proposed algorithm imposes relaxed non-negativity in the direct domain along with spatial-spectral regularizations in a transformed domain. The optimization problem is efficiently solved in a two-step approach using the concept of proximity operators. Vertex component analysis (VCA) is proposed to estimate the number of sources. Comparisons with state-of-the-art BSS algorithms on in-vivo MRSI data show the efficiency of the proposed algorithm. The presented method provides patterns that can easily be related to a specific tissue (normal, tumor, necrosis, hypoxia, edema or infiltration). Unlike other BSS methods dedicated to MRSI data, it can handle spectra with negative peaks and results are not sensitive to the initialization strategy. In addition, it is robust against noisy or bad-quality spectra.

Original languageEnglish
Title of host publication2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)
PublisherIEEE
Pages952-955
Number of pages4
ISBN (Electronic)9781479923496
DOIs
Publication statusPublished - 16 Jun 2016
Event13th IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2016 - Prague, Czech Republic
Duration: 13 Apr 201616 Apr 2016

Publication series

NameInternational Symposium on Biomedical Imaging
ISSN (Electronic)1945-8452

Conference

Conference13th IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2016
Abbreviated titleISBI 2016
CountryCzech Republic
CityPrague
Period13/04/1616/04/16

Keywords

  • blind source separation (BSS)
  • MRSI
  • tissue patterns

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'MRSI data unmixing using spatial and spectral priors in transformed domains'. Together they form a unique fingerprint.

Cite this