Título
Brain Tumor Tissue Segmentation in Multimodal Images
Autor
ELISEE ILUNGA MBUYAMBA
Colaborador
Claire Chalopin (Director)
Nivel de Acceso
Acceso Abierto
Materias
Resumen o descripción
Brain tumor is one of the main cause of death in the world. Its possible treatment consists in a surgery performed by neurosurgeons who open the skull (called craniotomy) for removing abnormal cells. After tumor resection, patients benefit of improved survival and life quality. Multimodal images, preoperative Magnetic Resonance Imaging (MRI) and intraoperative Ultrasound (iUS) data, are in general used to support this complex surgical operation. Preoperative images allow the tumor diagnosis and the surgery planning. Intraoperative data provide an update in the visualization of the brain during the operation and enable the control of resection. Indeed, geometrical parameters like tumor volume, position and distance to risk structures are needed for the success of the surgery. Thus, the detection and extraction of tumorous tissues are important. In this work, the brain tumor segmentation in multimodal images is addressed. Tumorous tissue extraction consists in three main stages. First, alternative methods for brain tumor segmentation in MRI are proposed. Second, the tumor delineation in iUS using a patient specifc MR tumor model is suggested. Third, an approach based on the fusion of intraoperative B-mode and contrast-Enhanced Ultrasound (CEUS) data is suggested for detection of tumor residuals in iUS.
Editor
Universidad de Guanajuato
Fecha de publicación
agosto de 2017
Tipo de publicación
Tesis de doctorado
Versión de la publicación
Versión publicada
Recurso de información
Formato
application/pdf
Idioma
Inglés
Repositorio Orígen
Repositorio Institucional de la Universidad de Guanajuato
Descargas
0