TY - JOUR
T1 - The effect of combining two echo times in automatic brain tumor classification by MRS
AU - García-Gómez, Juan M.
AU - Tortajada, Salvador
AU - Vidal, César
AU - Julià-Sape, Margarida
AU - Luts, Jan
AU - Moreno-Torres, Angel
AU - Van Huffel, Sabine
AU - Arús, Carles
AU - Robles, Montserrat
PY - 2008/12/1
Y1 - 2008/12/1
N2 - 1H MRS is becoming an accurate, non-invasive technique for initial examination of brain masses. We investigated if the combination of sing le-voxel 1H MRS at 1.5 T at two different (TEs), 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-TEs 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. © 2008 John Wiley & Sons, Ltd.
AB - 1H MRS is becoming an accurate, non-invasive technique for initial examination of brain masses. We investigated if the combination of sing le-voxel 1H MRS at 1.5 T at two different (TEs), 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-TEs 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. © 2008 John Wiley & Sons, Ltd.
KW - 1 H MRS
KW - Brain
KW - Cancer
KW - Decision support systems
KW - Long TE
KW - Pattern recognition
KW - Short TE
U2 - https://doi.org/10.1002/nbm.1288
DO - https://doi.org/10.1002/nbm.1288
M3 - Article
VL - 21
SP - 1112
EP - 1125
JO - NMR in Biomedicine
JF - NMR in Biomedicine
SN - 0952-3480
ER -