Paper Info
Title
Brain tumor segmentation from multiple MRI sequences using multiple kernel learning
Abstract
We propose a brain tumor segmentation method from multi-spectral MRI images. First, a large set of features based on wavelet coefficients, is computed on all types of images for a small number of voxels, allowing us to build a training feature base which is not homogeneous due to different types of image. The segmentation task is then viewed as a learning problem where only the most significant features from the feature base should be selected and then a classifier can be used. The new idea is to use Multiple Kernel Learning (MKL) by associating one or more kernels to each feature in order to solve jointly the two problems: selection of the features and their corresponding kernels and training of the classifier. All types of images are then segmented using the trained classifier on the selected features. Our algorithm was tested on the real data provided by the challenge of Brats 2012 and was compared to the resulting top methods. The results show good performance of our method.
Year
DOI
Venue
2014
10.1109/ICIP.2014.7025378
Image Processing
Keywords
Field
DocType
biomedical MRI,brain,feature extraction,feature selection,image classification,image segmentation,image sequences,medical image processing,tumours,brain tumor segmentation,feature selection,multiple MRI sequences,multiple kernel learning,multispectral MRI images,wavelet coefficients,Cerebral MRI,classification,feature selection,multiclass,multimodal,multiple kernel learning,segmentation,tumor
Computer vision,Scale-space segmentation,Feature selection,Pattern recognition,Computer science,Segmentation,Feature (computer vision),Multiple kernel learning,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Classifier (linguistics)
Conference
ISSN
Citations 
PageRank 
1522-4880
0
0.34
References 
Authors
6
4
Name
Order
Citations
PageRank
Naouel Boughattas100.34
Maxime Berar200.34
Kamel Hamrouni300.34
Ruan Su455953.00