Random decision forests for automatic brain tumor segmentation on multi-modal MRI images

dc.contributor.authorPinto, Adrianopor
dc.contributor.authorPereira, Sergiopor
dc.contributor.authorDinis, Hugopor
dc.contributor.authorSilva, Carlos A.por
dc.contributor.authorRasteiro, Deolinda M. L. D.por
dc.date.accessioned2018-03-01T19:47:36Z
dc.date.issued2015-01-01
dc.date.updated2018-03-01T19:16:47Z
dc.description.abstractBrain tumour segmentation from Magnetic Resonance Imaging (MRI) scans have an important role in the early tumour diagnosis and radiotherapy planning. However, MRI images of the brain contain complex characteristics, such as high diversity in tumour appearance and ambiguous tumour boundaries, even when using multi-sequence MRI images. We propose a fully automatic segmentation algorithm based on a Random Decision Forest, using a k-fold cross-validation approach. The extracted features are the intensity complemented with other appearance and context based features. The post-processing phase has a morphological filter to deal with misclassification errors. Our method is capable of detecting the tumour and segmenting the different tumorous tissues of the glioma achieving competitive results.por
dc.description.publicationversioninfo:eu-repo/semantics/publishedVersionpor
dc.distributioninternationalpor
dc.identifier.doi10.1109/ENBENG.2015.7088842por
dc.identifier.isbn9781479982691por
dc.identifier.urihttps://hdl.handle.net/1822/51372
dc.language.isoengpor
dc.peerreviewedyespor
dc.publisherIEEEpor
dc.rightsclosedAccesspor
dc.subjectMRIpor
dc.subjectBrain Tumour Segmentationpor
dc.subjectRandom Forestpor
dc.subject.wosScience & Technology
dc.titleRandom decision forests for automatic brain tumor segmentation on multi-modal MRI imagespor
dc.typeconferencePaperpor
dspace.entity.typePublicationen
sdum.bookTitle2015 IEEE 4TH PORTUGUESE MEETING ON BIOENGINEERING (ENBENG)
sdum.export.identifier4133

Ficheiros

Pacote original

A mostrar 1 - 1 de 1
A carregar...
Nome:
BRATS-RF.pdf
Tamanho:
2.34 MB
Formato:
Adobe Portable Document Format