The invention relates to a method for the characterisation and classification of kidney stones, comprising the following steps in which: (a) a plurality of samples of kidney stones are obtained and cut in order to observe the interior thereof, obtaining the flattest surface possible; (b) hyperspectral imaging (HSI) is used to obtain the spectra of the pre-cut kidney stones, with a plurality of regions of interest (ROI) being selected and the image being analysed using principal component analysis (PCA); (c) the main species are identified using factor analysis (FA); (d) atypical values are identified using principal component analysis (PCA); (e) the different types of kidney stones are analysed using principal component analysis (PCA); and (f) the artificial neural network (ANN) technique is applied to the data obtained from the principal component analysis (PCA) for the classification thereof.
Method for the Characterization and classification of kidney stones / Blanco, F.; Bonifazi, Giuseppe; Gargiulo, Aldo; Havel, J.; Lopez, M.; Serranti, Silvia; Valiente, M.. - (2011).
Method for the Characterization and classification of kidney stones
BONIFAZI, Giuseppe;GARGIULO, ALDO;SERRANTI, Silvia;
2011
Abstract
The invention relates to a method for the characterisation and classification of kidney stones, comprising the following steps in which: (a) a plurality of samples of kidney stones are obtained and cut in order to observe the interior thereof, obtaining the flattest surface possible; (b) hyperspectral imaging (HSI) is used to obtain the spectra of the pre-cut kidney stones, with a plurality of regions of interest (ROI) being selected and the image being analysed using principal component analysis (PCA); (c) the main species are identified using factor analysis (FA); (d) atypical values are identified using principal component analysis (PCA); (e) the different types of kidney stones are analysed using principal component analysis (PCA); and (f) the artificial neural network (ANN) technique is applied to the data obtained from the principal component analysis (PCA) for the classification thereof.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.