Brain tumor classification based on long echo proton MRS signals

被引:135
作者
Lukas, L
Devos, A
Suykens, JAK
Vanhamme, L
Howe, FA
Majós, C
Moreno-Torres, A
Van Der Graaf, M
Tate, AR
Arús, C
Van Huffel, S
机构
[1] Katholieke Univ Leuven, Dept Elect Engn, SCD, SISTA, B-3001 Heverlee, Belgium
[2] St George Hosp, Sch Med, Dept Biochem & Immunol, CRC Biomed Magnet Resonance Res Grp, London SW17 0RE, England
[3] Hosp Llobregat, IDI, CSU Bellvitge, Barcelona 08907, Spain
[4] Ctr Diagnost Pedralbes, Esplugas de Llobregat 08950, Spain
[5] Univ Nijmegen, Med Ctr, Dept Radiol, NL-6500 HB Nijmegen, Netherlands
[6] Univ Autonoma Barcelona, Dept Bioquim & Biol Mol, Unitat Ciencias, E-08193 Barcelona, Spain
关键词
brain tumors; classification; magnetic resonance spectroscopy (MRS); Linear discriminant analysis (LDA); support vector machine (SVM); least squares support vector machine (LS-SVM);
D O I
10.1016/j.artmed.2004.01.001
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
There has been a growing research interest in brain tumor classification based on proton magnetic resonance spectroscopy (H-1 MRS) signals. Four research centers within the EU funded INTERPRET project have acquired a significant number of long echo H-1 MRS signals for brain tumor classification. In this paper, we present an objective comparison of several classification techniques applied to the discrimination of four types of brain tumors: meningiomas, glioblastomas, astrocytomas grade II and metastases. Linear and non-linear classifiers are compared: linear discriminant analysis (LDA), support vector machines (SVM) and least squares SVM (LS-SVM) with a linear kernel as linear techniques and LS-SVM with a radial basis function (RBF) kernel as a non-linear technique. Kernel-based methods can perform well in processing high dimensional data. This motivates the inclusion of SVM and LS-SVM in this study. The analysis includes optimal input variable selection, (hyper-) parameter estimation, followed by performance evaluation. The classification performance is evaluated over 200 stratified random samplings of the dataset into training and test sets. Receiver operating characteristic (ROC) curve analysis measures the performance of binary classification, while for multiclass classification, we consider the accuracy as performance measure. Based on the complete magnitude spectra, automated binary classifiers are able to reach an area under the ROC curve (AUC) of more than 0.9 except for the hard case glioblastomas versus metastases. Although, based on the available long echo H-1 MRS data, we did not find any statistically significant difference between the performances of LDA and the kernel-based methods, the latter have the strength that no dimensionality reduction is required to obtain such a high performance. (C) 2004 Elsevier B.V. All rights reserved.
引用
收藏
页码:73 / 89
页数:17
相关论文
共 42 条
[1]  
[Anonymous], 2002, Least Squares Support Vector Machines
[2]   IMPROVED ALGORITHM FOR NONITERATIVE TIME-DOMAIN MODEL-FITTING TO EXPONENTIALLY DAMPED MAGNETIC-RESONANCE SIGNALS [J].
BARKHUIJSEN, H ;
DEBEER, R ;
VANORMONDT, D .
JOURNAL OF MAGNETIC RESONANCE, 1987, 73 (03) :553-557
[3]   CLINICAL MR SPECTROSCOPY - FUNDAMENTALS, CURRENT APPLICATIONS, AND FUTURE POTENTIAL [J].
COUSINS, JP .
AMERICAN JOURNAL OF ROENTGENOLOGY, 1995, 164 (06) :1337-1347
[4]   A new approach for analyzing proton magnetic resonance spectroscopic images of brain tumors:: nosologic images [J].
De Edeleny, FS ;
Rubin, C ;
Estève, F ;
Grand, S ;
Décorps, M ;
Lefournier, V ;
Le Bas, JF ;
Rémy, C .
NATURE MEDICINE, 2000, 6 (11) :1287-1289
[5]  
DEEDELENYI FS, 2002, P 19 ANN M EUR SOC M, P91
[6]   COUPLING EFFECTS IN VOLUME SELECTIVE H-1 SPECTROSCOPY OF MAJOR BRAIN-METABOLITES [J].
ERNST, T ;
HENNIG, J .
MAGNETIC RESONANCE IN MEDICINE, 1991, 21 (01) :82-96
[7]  
Govindaraju V, 2000, NMR BIOMED, V13, P129, DOI 10.1002/1099-1492(200005)13:3<129::AID-NBM619>3.0.CO
[8]  
2-V
[9]  
GUNN SR, 1997, SUPPORT VECTOR MACHI
[10]   A METHOD OF COMPARING THE AREAS UNDER RECEIVER OPERATING CHARACTERISTIC CURVES DERIVED FROM THE SAME CASES [J].
HANLEY, JA ;
MCNEIL, BJ .
RADIOLOGY, 1983, 148 (03) :839-843