Descripción
|
|
---|---|
Gliomas are the most common form of primary brain tumours in adults, being the glioblastoma tumour the most frequent and dangerous type. An accurate radical resection of the tumour allows incrementing the survival rates of the patients. Hyperspectral Imaging is an emerging technology for medical diagnosis issues due to the fact that it is a non-contact, non-ionizing and non-invasive sensing technique. The work presented in this paper tries to establish a novel way in the use of hyperspectral images to help neurosurgeons to accurately determine the tumour boundaries in the process of brain tumour resection, avoiding excessive extraction of healthy tissue and the accidental leaving of un-resected small tumour tissues. As classification framework for this study, a hybrid supervised-unsupervised classification method is proposed. This method relies in a spatial-spectral classification method based on a pixel-wise Support Vector Machines and a K-Nearest Neighbours spatial filtering. A segmentation map obtained through Hierarchical K-Means is fused with the supervised classification map using a majority voting scheme. | |
Internacional
|
Si |
Nombre congreso
|
XXXI Design of Circuits and Integrated Systems Conference |
Tipo de participación
|
960 |
Lugar del congreso
|
Granada, Spain |
Revisores
|
Si |
ISBN o ISSN
|
978-1-5090-4565-5 |
DOI
|
|
Fecha inicio congreso
|
23/11/2016 |
Fecha fin congreso
|
25/11/2016 |
Desde la página
|
1 |
Hasta la página
|
6 |
Título de las actas
|
Proceedings of the XXXI Design of Circuits and Integrated Systems Conference |