- -

Incremental gaussian discriminant analysis based on graybill and deal weighted combination of estimators for brain tumour diagnosis

RiuNet: Institutional repository of the Polithecnic University of Valencia

Share/Send to

Cited by

Statistics

Incremental gaussian discriminant analysis based on graybill and deal weighted combination of estimators for brain tumour diagnosis

Show simple item record

Files in this item

dc.contributor.author Tortajada Velert, Salvador es_ES
dc.contributor.author Fuster García, Elíes es_ES
dc.contributor.author Vicente Robledo, Javier es_ES
dc.contributor.author Wesseling, Pieter es_ES
dc.contributor.author Howe, Franklyn es_ES
dc.contributor.author Julià-Sapé, Margarida es_ES
dc.contributor.author Candiota, Ana-Paula es_ES
dc.contributor.author Monleón, Daniel es_ES
dc.contributor.author Moreno-Torres, Àngel es_ES
dc.contributor.author Pujol, Jesús es_ES
dc.contributor.author Griffiths, Jonh R. es_ES
dc.contributor.author Wright, Alan es_ES
dc.contributor.author Peet, Andrew C. es_ES
dc.contributor.author Martínez-Bisbal, M. Carmen es_ES
dc.contributor.author Celda, Bernardo es_ES
dc.contributor.author Arús, Carles es_ES
dc.contributor.author Robles Viejo, Montserrat es_ES
dc.contributor.author García Gómez, Juan Miguel es_ES
dc.date.accessioned 2014-05-14T12:17:05Z
dc.date.issued 2011-08
dc.identifier.issn 1532-0464
dc.identifier.uri http://hdl.handle.net/10251/37477
dc.description.abstract In the last decade, machine learning (ML) techniques have been used for developing classifiers for automatic brain tumour diagnosis. However, the development of these ML models rely on a unique training set and learning stops once this set has been processed. Training these classifiers requires a representative amount of data, but the gathering, preprocess, and validation of samples is expensive and time-consuming. Therefore, for a classical, non-incremental approach to ML, it is necessary to wait long enough to collect all the required data. In contrast, an incremental learning approach may allow us to build an initial classifier with a smaller number of samples and update it incrementally when new data are collected. In this study, an incremental learning algorithm for Gaussian Discriminant Analysis (iGDA) based on the Graybill and Deal weighted combination of estimators is introduced. Each time a new set of data becomes available, a new estimation is carried out and a combination with a previous estimation is performed. iGDA does not require access to the previously used data and is able to include new classes that were not in the original analysis, thus allowing the customization of the models to the distribution of data at a particular clinical center. An evaluation using five benchmark databases has been used to evaluate the behaviour of the iGDA algorithm in terms of stability-plasticity, class inclusion and order effect. Finally, the iGDA algorithm has been applied to automatic brain tumour classification with magnetic resonance spectroscopy, and compared with two state-of-the-art incremental algorithms. The empirical results obtained show the ability of the algorithm to learn in an incremental fashion, improving the performance of the models when new information is available, and converging in the course of time. Furthermore, the algorithm shows a negligible instance and concept order effect, avoiding the bias that such effects could introduce. © 2011 Elsevier Inc. es_ES
dc.description.sponsorship This work has been partially funded by the Spanish Institut de Salud Carlos III (ISCiii) through the RETICS Combiomed (RD07/0067/2001). The authors thank the Programa Torres Quevedo from Ministerio de Educacion y Ciencia, co-founded by the European Social Fund (PTQ05-02-03386 and PTQ08-01-06802). We thank eTUMOUR, HEALTHAGENTS and INTERPRET partners for providing data, in particular W. Gajewicz (MUL), J. Calvar (FLENI), A. Heerschap (RUNMC), J. Capellades (IDI-Badalona), C. Majos (IDI-Bellvitge), and W. Semmier (DKFZ-Heidelberg). CIBER-BBN is an initiative funded by the VI National R&D&D&I Plan 2008-2011, CIBER Actions are financed by the Institut de Salud Carlos III with assistance from the European Regional Development Fund. en_EN
dc.format.extent 11 es_ES
dc.language Inglés es_ES
dc.publisher Elsevier es_ES
dc.relation.ispartof Journal of Biomedical Informatics es_ES
dc.rights Reserva de todos los derechos es_ES
dc.subject Machine learning es_ES
dc.subject Incremental learning es_ES
dc.subject Graybill-Deal estimator es_ES
dc.subject Automatic brain tumour diagnosis es_ES
dc.subject Magnetic resonance es_ES
dc.subject Brain tumours es_ES
dc.subject Empirical results es_ES
dc.subject Gaussians es_ES
dc.subject Incremental algorithm es_ES
dc.subject Number of samples es_ES
dc.subject Preprocess es_ES
dc.subject Training sets es_ES
dc.subject Discriminant analysis es_ES
dc.subject Estimation es_ES
dc.subject Magnetic resonance spectroscopy es_ES
dc.subject.classification FISICA APLICADA es_ES
dc.title Incremental gaussian discriminant analysis based on graybill and deal weighted combination of estimators for brain tumour diagnosis es_ES
dc.type Artículo es_ES
dc.embargo.lift 10000-01-01
dc.embargo.terms forever es_ES
dc.identifier.doi 10.1016/j.jbi.2011.02.009
dc.relation.projectID info:eu-repo/grantAgreement/MICINN//RD07%2F0067%2F2001/ES/RED TEMÁTICA DE INVESTIGACIÓN COOPERATIVA EN BIOMEDICINA COMPUTACIONAL/ / es_ES
dc.relation.projectID info:eu-repo/grantAgreement/MEC//PTQ05-02-03386/ES/PTQ05-02-03386/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/MICINN//PTQ-08-01-06802/ES/PTQ-08-01-06802/ es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Instituto Universitario de Aplicaciones de las Tecnologías de la Información - Institut Universitari d'Aplicacions de les Tecnologies de la Informació es_ES
dc.contributor.affiliation Universitat Politècnica de València. Departamento de Física Aplicada - Departament de Física Aplicada es_ES
dc.description.bibliographicCitation Tortajada Velert, S.; Fuster García, E.; Vicente Robledo, J.; Wesseling, P.; Howe, F.; Julià-Sapé, M.; Candiota, A.... (2011). Incremental gaussian discriminant analysis based on graybill and deal weighted combination of estimators for brain tumour diagnosis. Journal of Biomedical Informatics. 44(4):677-687. https://doi.org/10.1016/j.jbi.2011.02.009 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion http://dx.doi.org/10.1016/j.jbi.2011.02.009 es_ES
dc.description.upvformatpinicio 677 es_ES
dc.description.upvformatpfin 687 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 44 es_ES
dc.description.issue 4 es_ES
dc.relation.senia 217422
dc.contributor.funder Ministerio de Educación y Ciencia es_ES
dc.contributor.funder Ministerio de Ciencia e Innovación es_ES
dc.contributor.funder Ministerio de Ciencia e Innovación es_ES
dc.contributor.funder Instituto de Salud Carlos III es_ES


This item appears in the following Collection(s)

Show simple item record