
Automated Brain-Tissue Segmentation by Multi-Feature SVM Classification
Please use this identifier to cite or link to this publication: http://hdl.handle.net/10380/3443 |
Published in The MIDAS Journal - The MICCAI Grand Challenge on MR Brain Image Segmentation (MRBrainS13) .
Submitted by Annegreet Van opbroek on 10-23-2013.
We present a method for automated brain-tissue segmentation through voxelwise classification. Our algorithm uses manually labeled training images to train a support vector machine (SVM) classifier, which is then used for the segmentation of target images. The classification incorporates voxel intensities from a T1-weighted scan, an IR scan, and a FLAIR scan; features to encode the voxel position in the image; and Gaussian-scale-space features and Gaussian-derivative features at
multiple scales to facilitate a smooth segmentation.
An experiment on data from the MRBrainS13 brain-tissue-segmentation challenge showed that our algorithm produces reasonable segmentations in a reasonable amount of time.
multiple scales to facilitate a smooth segmentation.
An experiment on data from the MRBrainS13 brain-tissue-segmentation challenge showed that our algorithm produces reasonable segmentations in a reasonable amount of time.
Reviews
Quick Comments
Resources
![]() |
|
Download All | |
Download Paper , View Paper |
Statistics more
![]() |
|
Global rating: | ![]() ![]() ![]() ![]() ![]() |
Review rating: | ![]() ![]() ![]() ![]() ![]() |
Paper Quality: |
![]() ![]() |
Information more
![]() |
|
Categories: | Classification, Mathematics, Segmentation |
Keywords: | Machine Learning, Pattern Recognition, Classification, Segmentation, Brain, MRI |
Tracking Number: | NWO 639.022.010 |
Export citation: |
Share
![]() |
Linked Publications more
![]() |
||
![]() by Rabiei H., Richard F., Roth M., Anton J., Coulon O., Lefevre J.
|
||
![]() by Orasanu E., Melbourne A., Lorenzi M., Modat M., Lombaert H., Eaton-Rosen Z., Robertson N.J., Kendall G.S., Marlow N., Ourselin S.
|
View license
Loading license...
Send a message to the author
