Premium
The effect of combining two echo times in automatic brain tumor classification by MRS
Author(s) -
GarcíaGómez Juan M.,
Tortajada Salvador,
Vidal César,
JuliàSapé Margarida,
Luts Jan,
MorenoTorres Àngel,
Van Huffel Sabine,
Arús Carles,
Robles Montserrat
Publication year - 2008
Publication title -
nmr in biomedicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.278
H-Index - 114
eISSN - 1099-1492
pISSN - 0952-3480
DOI - 10.1002/nbm.1288
Subject(s) - artificial intelligence , linear discriminant analysis , support vector machine , pattern recognition (psychology) , voxel , computer science , classifier (uml) , glioblastoma , glioma , anaplastic astrocytoma , brain tumor , astrocytoma , machine learning , medicine , pathology , cancer research
1 H MRS is becoming an accurate, non‐invasive technique for initial examination of brain masses. We investigated if the combination of single‐voxel 1 H MRS at 1.5 T at two different ( TE s), short TE (PRESS or STEAM, 20–32 ms) and long TE (PRESS, 135–136 ms), improves the classification of brain tumors over using only one echo TE . A clinically validated dataset of 50 low‐grade meningiomas, 105 aggressive tumors (glioblastoma and metastasis), and 30 low‐grade glial tumors (astrocytomas grade II, oligodendrogliomas and oligoastrocytomas) was used to fit predictive models based on the combination of features from short‐ TE s and long‐ TE spectra. A new approach that combines the two consecutively was used to produce a single data vector from which relevant features of the two TE spectra could be extracted by means of three algorithms: stepwise, reliefF, and principal components analysis. Least squares support vector machines and linear discriminant analysis were applied to fit the pairwise and multiclass classifiers, respectively. Significant differences in performance were found when short‐ TE , long‐ TE or both spectra combined were used as input. In our dataset, to discriminate meningiomas, the combination of the two TE acquisitions produced optimal performance. To discriminate aggressive tumors from low‐grade glial tumours, the use of short‐ TE acquisition alone was preferable. The classifier development strategy used here lends itself to automated learning and test performance processes, which may be of use for future web‐based multicentric classifier development studies. Copyright © 2008 John Wiley & Sons, Ltd.