A new label fusion method using graph cuts: application to hippocampus segmentation

Platero Dueñas, Carlos ORCID: https://orcid.org/0000-0003-3712-8297, Tobar Puente, M. del Carmen ORCID: https://orcid.org/0000-0002-7370-6835, Sanguino Botella, Fco. Javier ORCID: https://orcid.org/0000-0002-9203-101X and Velasco Manuel, Olga ORCID: https://orcid.org/0000-0002-6774-6590 (2014). A new label fusion method using graph cuts: application to hippocampus segmentation. En: "XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013 / MEDICON 2013, 25-28 September 2013, Seville, Spain", 25/09/2013 - 28/09/2013, Sevilla, España. ISBN 978-3-319-00845-5. pp. 174-177. https://doi.org/10.1007/978-3-319-00846-2_43.

Descripción

Título: A new label fusion method using graph cuts: application to hippocampus segmentation
Autor/es:
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013 / MEDICON 2013, 25-28 September 2013, Seville, Spain
Fechas del Evento: 25/09/2013 - 28/09/2013
Lugar del Evento: Sevilla, España
Título del Libro: XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013: IFMBE Proceedings
Fecha: 2014
ISBN: 978-3-319-00845-5
Volumen: 41
Materias:
ODS:
Palabras Clave Informales: Label fusion; Atlas-based segmentation; Hippocampus segmentation
Escuela: E.T.S.I. Diseño Industrial (UPM)
Departamento: Electrónica, Automática e Informática Industrial [hasta 2014]
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[thumbnail of INVE_MEM_2013_180198.pdf]
Vista Previa
PDF (Portable Document Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (464kB) | Vista Previa

Resumen

The aim of this paper is to develop a probabilistic modeling framework for the segmentation of structures of interest from a collection of atlases. Given a subset of registered atlases into the target image for a particular Region of Interest (ROI), a statistical model of appearance and shape is computed for fusing the labels. Segmentations are obtained by minimizing an energy function associated with the proposed model, using a graph-cut technique. We test different label fusion methods on publicly available MR images of human brains.

Más información

ID de Registro: 33313
Identificador DC: https://oa.upm.es/33313/
Identificador OAI: oai:oa.upm.es:33313
URL Portal Científico: https://portalcientifico.upm.es/es/ipublic/item/9271229
Identificador DOI: 10.1007/978-3-319-00846-2_43
URL Oficial: http://link.springer.com/chapter/10.1007/978-3-319...
Depositado por: Memoria Investigacion
Depositado el: 02 Feb 2015 12:55
Ultima Modificación: 26 Ene 2026 13:38