Quantitative combination of volumetric MR imaging and MR spectroscopy data for the discrimination of meningiomas from metastatic brain tumors by means of pattern recognition

被引：17

作者：

Georgiadis, Pantelis ^{[1
]}

Kostopoulos, Spiros ^{[2
]}

Cavouras, Dionisis ^{[2
]}

Glotsos, Dimitris ^{[2
]}

Kalatzis, Ioannis ^{[2
]}

Sifaki, Koralia ^{[3
]}

Malamas, Menelaos ^{[3
]}

Solomou, Ekaterini ^{[4
]}

Nikiforidis, George ^{[1
]}

机构：

[1] Univ Patras, Fac Med, Lab Med Phys, MIPA Grp, GR-26503 Rion, Greece

[2] Inst Educ Technol, Dept Med Instruments Technol, Med Image & Signal Proc Lab, GR-12210 Athens, Greece

[3] 251 Gen Hellen AF Hosp, MRI Unit, GR-11525 Athens, Greece

[4] Univ Patras, Fac Med, Dept Radiol, GR-26503 Rion, Greece

来源：

MAGNETIC RESONANCE IMAGING | 2011年 / 29卷 / 04期

关键词：

Brain Tumors; MRI; MRS; Volumetric textural features; Spectroscopic features; Pattern classification; MAGNETIC-RESONANCE SPECTROSCOPY; PROBABILISTIC NEURAL-NETWORKS; SHORT ECHO TIME; TEXTURE ANALYSIS; CLASSIFICATION; FEATURES; TRANSFORMATION;

D O I：

10.1016/j.mri.2010.11.006

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

The analysis of information derived from magnetic resonance imaging (MRI) and spectroscopy (MRS) has been identified as an important indicator for discriminating among different brain pathologies. The purpose of this study was to investigate the efficiency of the combination of textural MRI features and MRS metabolite ratios by means of a pattern recognition system in the task of discriminating between meningiomas and metastatic brain tumors. The data set consisted of 40 brain MR image series and their corresponding spectral data obtained from patients with verified tumors. The pattern recognition system was designed employing the support vector machines classifier with radial basis function kernel; the system was evaluated using an external cross validation process to render results indicative of the generalization performance to "unknown" cases. The combination of MR textural and spectroscopic features resulted in 92.15% overall accuracy in discriminating meningiomas from metastatic brain tumors. The fusion of the information derived from MRI and MRS data might be helpful in providing clinicians a useful second opinion tool for accurate characterization of brain tumors. (c) 2011 Elsevier Inc. All rights reserved.

引用

页码：525 / 535

页数：11

共 40 条

[1] Selection bias in gene extraction on the basis of microarray gene-expression data [J].

Ambroise, C ;

McLachlan, GJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2002, 99 (10) :6562-6566

[2]

BRANDAO L, 2003, SPECTROSCOPY BRAIN

[3] 1H MR spectroscopy of human brain tumours:: a practical approach [J].

Callot, Virginie ;

Galanaud, Damien ;

Le Fur, Yann ;

Confort-Gouny, Sylviane ;

Ranjeva, Jean-Philippe ;

Cozzone, Patrick J. .

EUROPEAN JOURNAL OF RADIOLOGY, 2008, 67 (02) :268-274

[4] Five-year survivors of brain metastases: A single-institution report of 32 patients [J].

Chao, Samuel T. ;

Barnett, Gene H. ;

Liu, Stephanie W. ;

Reuther, Alwyn M. ;

Toms, Steven A. ;

Vogelbaum, Michael A. ;

Videtic, Gregory M. M. ;

Suh, John H. .

INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 2006, 66 (03) :801-809

[5] 1H-MRS metabolic patterns for distinguishing between meningiomas and other brain tumors [J].

Cho, YD ;

Choi, GH ;

Lee, SP ;

Kim, JK .

MAGNETIC RESONANCE IMAGING, 2003, 21 (06) :663-672

[6] Single voxel proton MR spectroscopy findings of typical and atypical intracranial meningiomas [J].

Demir, Mustafa Kemal ;

Iplikcioglu, A. Celal ;

Dincer, Alp ;

Arslan, Mahmut ;

Sav, Aydin .

EUROPEAN JOURNAL OF RADIOLOGY, 2006, 60 (01) :48-55

[7] The use of multivariate MR imaging intensities versus metabolic data from MR spectroscopic imaging for brain tumour classification [J].

Devos, A ;

Simonetti, AW ;

van der Graaf, M ;

Lukas, L ;

Suykens, JAK ;

Vanhamme, L ;

Buydens, LMC ;

Heerschap, A ;

Van Huffel, S .

JOURNAL OF MAGNETIC RESONANCE, 2005, 173 (02) :218-228

[8] Classification of brain tumours using short echo time 1H MR spectra [J].

Devos, A ;

Lukas, L ;

Suykens, JAK ;

Vanhamme, L ;

Tate, AR ;

Howe, FA ;

Majós, C ;

Moreno-Torres, A ;

van der Graaf, M ;

Arús, C ;

Van Huffel, S .

JOURNAL OF MAGNETIC RESONANCE, 2004, 170 (01) :164-175

[9]

Galloway M. M., 1975, Comput. Graphic. Image Processing, V4, P172, DOI [10.1016/S0146-664X(75)80008-6, DOI 10.1016/S0146-664X(75)80008-6]

[10] Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features [J].

Georgiadis, Pantelis ;

Cavouras, Dionisis ;

Kalatzis, Ioannis ;

Daskalakis, Antonis ;

Kagadis, George C. ;

Sifaki, Koralia ;

Malamas, Menelaos ;

Nikiforidis, George ;

Solomou, Ekaterini .

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2008, 89 (01) :24-32

← 1 2 3 4 →