IQUIR 05412
INSTITUTO DE QUIMICA ROSARIO
Unidad Ejecutora - UE
artículos
Título:
Artificial Neural Networks to Evaluate the Boron Concentration Decreasing Profile in Blood-BPA Samples of BNCT Patients
Autor/es:
ALEJANDRO G. GARCÍA REIRIZ; JORGE F. MAGALLANES; JURE ZUPAN; SARA LIBERMAN
Revista:
APPLIED RADIATION AND ISOTOPES
Editorial:
PERGAMON-ELSEVIER SCIENCE LTD
Referencias:
Año: 2011 vol. 69 p. 1793 - 1795
ISSN:
0969-8043
Resumen:
For the prediction of decay concentration profiles of the p-boronophenylalanine (BPA) in bloodduring BNCT treatment a method is suggested based on Kohonen neural networks. The results of amodel trained with the concentration profiles from the literature are described.The prediction of the model was validated by the leave-one-out method. Its robustness shows that itis mostly independent on small variations. The ability to fit retrospective experimental data shows anuncertainty lower than the two compartment model used previously.
