Unsupervised glioblastoma segmentation based on multiparametric Magnetic Resonance Imaging (MRI)
[EN] Design and evaluation of an automated unsupervised segmentation method for brain tumour, specifically glioblastoma tumour, based on Magnetic Resonance Imaging (MRI). A preprocessing and feature extraction pipeline based on the state of the art techniques for MRI is proposed. Several unsupervise...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2014 |
| País: | España |
| Institución: | Universitat Politècnica de València (UPV) |
| Repositorio: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia |
| Idioma: | inglés |
| OAI Identifier: | oai:riunet.upv.es:10251/51064 |
| Acceso en línea: | https://riunet.upv.es/handle/10251/51064 |
| Access Level: | acceso abierto |
| Palabra clave: | Clasificación no supervisada Segmentación tumor cerebral Análisis de imagen médica Unsupervised classification Brain tumour segmentation Medical image analisis FISICA APLICADA LENGUAJES Y SISTEMAS INFORMATICOS Máster Universitario en Inteligencia Artificial, Reconocimiento de Formas e Imagen Digital-Màster Universitari en Intel·ligència Artificial, Reconeixement de Formes i Imatge Digital |
| Sumario: | [EN] Design and evaluation of an automated unsupervised segmentation method for brain tumour, specifically glioblastoma tumour, based on Magnetic Resonance Imaging (MRI). A preprocessing and feature extraction pipeline based on the state of the art techniques for MRI is proposed. Several unsupervised classification algorithms are studied and evaluated, considering structured and non structured classification algorithms. An original postprocessing method is designed to automatically identify the pathological classes of a segmentation. The unsupervised method is evaluated with a real public reference dataset, against consolidated supervised approaches. |
|---|