Computer-aided diagnosis of brain tumors using image enhancement and fuzzy logic

A robust medical image processing system depends upon a variety of aspects, including a proper image enhancement, and an optimal segmentation. An algorithm was proposed in this paper to facilitate the implementation of these two steps. First a Magnetic Resonance (MR) image is enhanced via spatial do...

Full description

Autores:
Vianney Kinani, Jean Marie
Rosales Silva, Alberto J.
Gallegos Funes, Francisco J.
Arellano, Alfonso
Tipo de recurso:
Article of journal
Fecha de publicación:
2014
Institución:
Universidad Nacional de Colombia
Repositorio:
Universidad Nacional de Colombia
Idioma:
spa
OAI Identifier:
oai:repositorio.unal.edu.co:unal/71810
Acceso en línea:
https://repositorio.unal.edu.co/handle/unal/71810
http://bdigital.unal.edu.co/36281/
Palabra clave:
MRI
Region of interest
Segmentation
Clustering.
MRI
Region of interest
Segmentation
Clustering
Rights
openAccess
License
Atribución-NoComercial 4.0 Internacional
Description
Summary:A robust medical image processing system depends upon a variety of aspects, including a proper image enhancement, and an optimal segmentation. An algorithm was proposed in this paper to facilitate the implementation of these two steps. First a Magnetic Resonance (MR) image is enhanced via spatial domain filtering and its contrast is improved, next, the image is segmented using fuzzy C-mean clustering, then the region of interest which might be the tumor or edema, is detected and delineated. The key advantage of this image processing pipeline is the simultaneous use of features computed from the intensity properties of the image in a cascading pattern which makes the computation self-contained. Performance evaluation of the proposed algorithm was carried out on brain images from different MRI’s and the algorithm proved to be successful, comparing it with other dedicated applications.