Low grade glioma segmentation using an automatic computational technique in magnetic resonance imaging

Through this work we propose a computational technique for the segmentation of a brain tumor, identified as low grade glioma (LGG), specifically grade II astrocytoma, which is present in magnetic resonance images (MRI). This technique consists of 3 stages developed in the three-dimensional domain. T...

Descripción completa

Detalles Bibliográficos
Autores: Vera, Miguel, Huérfano, Yoleidy, Valbuena, Oscar, Contreras, Yudith, Cuberos, María, Vivas, Marisela, Salazar, Williams, Vera, María Isabel, Borrero, Maryury, Hernández, Carlos, Barrera, Doris, Molina, Ángel Valentín, Martínez, Luis Javier, Salazar, Juan, Gelvez, Elkin, Sáenz, Frank
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2018
País:Colombia
Institución:Universidad Simón Bolívar
Repositorio:Repositorio Digital USB
Idioma:inglés
OAI Identifier:oai:bonga.unisimon.edu.co:20.500.12442/2525
Acceso en línea:http://hdl.handle.net/20.500.12442/2525
Access Level:acceso abierto
Palabra clave:Magnetic resonance brain imaging
Cerebral tumor
Low grade glioma
Grade II astrocytoma
Computational technique
Segmentation
Imágenes cerebrales por resonancia magnética
Tumor cerebral
Gliomas de bajo grado
Astrocitoma de grado II
Técnica computacional
Segmentación
Descripción
Sumario:Through this work we propose a computational technique for the segmentation of a brain tumor, identified as low grade glioma (LGG), specifically grade II astrocytoma, which is present in magnetic resonance images (MRI). This technique consists of 3 stages developed in the three-dimensional domain. They are: pre-processing, segmentation and postprocessing. The percent relative error (PrE) is considered to compare the segmentations of the LGG, generated by a neuro- oncologist manually, with the dilated segmentations of the LGG, obtained automatically. The combination of parameters linked to the lowest PrE, allow establishing the optimal parameters of each computational algorithm that makes up the proposed computational technique. The results allow reporting a PrE of 1.43%, which indicates an excellent correlation between the manual segmentations and those produced by the computational technique developed.

Similares en LA Referencia