Search | SciELO

OBJETIVO: Propor um sistema para segmentação automática de tumores do encéfalo. MÉTODOS: O sistema emprega parâmetros de textura como sua principal fonte de informação para a segmentação. RESULTADOS: Os acertos chegaram a 94% na correspondência entre a segmentação obtida e o padrão-ouro. CONCLUSÃO: Os resultados obtidos mostram que o sistema é capaz de localizar e delimitar as áreas de tumor sem necessidade de interação com o operador.

OBJECTIVE: To propose an automatic brain tumor segmentation system. METHODS: The system used texture characteristics as its main source of information for segmentation. RESULTS: The mean correct match was 94% of correspondence between the segmented areas and ground truth. CONCLUSION: Final results showed that the proposed system was able to find and delimit tumor areas without requiring any user interaction.

Index code	Element
ti	article title
au	author
kw	article keywords
subject	subject (title words, abstract and keywords)
ab	abstract
ta	journal short title (e.g. Cad. Saúde Pública)
journal_title	journal full title (e.g. Cadernos de Saúde Pública)
la	publication language code (e.g. pt - Portuguese, es - Spanish)
type	document type
pid	publication identifier
publication_year	publication year of publication
sponsor	sponsor
aff_country	country code of the author's affiliation
aff_institution	author affiliation institution
volume	article volume
issue	article issue
elocation	elocation
doi	DOI number
issn	journal ISSN
in	SciELO colection code (e.g. scl - Brasil, col - Colômbia)
use_license	article usage license code

No documents were found for your search