Classification, dimensionality reduction, and maximally discriminatory visualization of a multicentre H-MRS database of brain tumors

Paulo J.G. Lisboa; Enrique Romero; Alfredo Vellido; Margarida Julià-Sapé; Carles Arüs

doi:10.1109/ICMLA.2008.20

Classification, dimensionality reduction, and maximally discriminatory visualization of a multicentre ^H-MRS database of brain tumors

Paulo J.G. Lisboa, Enrique Romero, Alfredo Vellido, Margarida Julià-Sapé, Carles Arüs

Departament de Bioquímica i de Biologia Molecular

Producció científica: Altres contribucions

9 Cites (Scopus)

Resum

The combination of an Artificial Neural Network classifier, a feature selection process, and a novel linear dimensionality reduction technique that provides a data projection for visualization and which preserves completely the class discrimination achieved by the classifier, is applied in this study to the analysis of an international, multi-centre ¹H-MRS database of brain tumors. This combination yields results that are both intuitively interpretable and. very accurate. The method as a whole remains simple enough as to allow its easy integration in existing medical decision support systems.

Idioma original	Anglès
Nombre de pàgines	6
DOIs	https://doi.org/10.1109/ICMLA.2008.20
Estat de la publicació	Publicada - 2008

Sèrie de publicacions

Nom	Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008

Accés al document

10.1109/ICMLA.2008.20

Altres arxius i enllaços

Enllaç a la publicació de Scopus

Com citar-ho

@misc{bb1ac75c9185469295be33e76b0d47c8,

title = "Classification, dimensionality reduction, and maximally discriminatory visualization of a multicentre H-MRS database of brain tumors",

abstract = "The combination of an Artificial Neural Network classifier, a feature selection process, and a novel linear dimensionality reduction technique that provides a data projection for visualization and which preserves completely the class discrimination achieved by the classifier, is applied in this study to the analysis of an international, multi-centre 1H-MRS database of brain tumors. This combination yields results that are both intuitively interpretable and. very accurate. The method as a whole remains simple enough as to allow its easy integration in existing medical decision support systems.",

author = "Lisboa, {Paulo J.G.} and Enrique Romero and Alfredo Vellido and Margarida Juli{\`a}-Sap{\'e} and Carles Ar{\"u}s",

year = "2008",

doi = "10.1109/ICMLA.2008.20",

language = "English",

isbn = "9780769534954",

series = "Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008",

type = "Other",

}

TY - GEN

T1 - Classification, dimensionality reduction, and maximally discriminatory visualization of a multicentre H-MRS database of brain tumors

AU - Lisboa, Paulo J.G.

AU - Romero, Enrique

AU - Vellido, Alfredo

AU - Julià-Sapé, Margarida

AU - Arüs, Carles

PY - 2008

Y1 - 2008

N2 - The combination of an Artificial Neural Network classifier, a feature selection process, and a novel linear dimensionality reduction technique that provides a data projection for visualization and which preserves completely the class discrimination achieved by the classifier, is applied in this study to the analysis of an international, multi-centre 1H-MRS database of brain tumors. This combination yields results that are both intuitively interpretable and. very accurate. The method as a whole remains simple enough as to allow its easy integration in existing medical decision support systems.

AB - The combination of an Artificial Neural Network classifier, a feature selection process, and a novel linear dimensionality reduction technique that provides a data projection for visualization and which preserves completely the class discrimination achieved by the classifier, is applied in this study to the analysis of an international, multi-centre 1H-MRS database of brain tumors. This combination yields results that are both intuitively interpretable and. very accurate. The method as a whole remains simple enough as to allow its easy integration in existing medical decision support systems.

UR - http://www.scopus.com/inward/record.url?scp=60649096874&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2008.20

DO - 10.1109/ICMLA.2008.20

M3 - Other contribution

AN - SCOPUS:60649096874

SN - 9780769534954

T3 - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008

ER -