Name
Abstract | ||
|---|---|---|
This paper presents a new brain injury detection approach in images acquired by magnetic resonance imaging (MRI). The proposed approach is based on the fact that the anatomical structure of a 2D brain is highly symmetric, while most of the injury in the brain generally indicates asymmetry. The approach starts from symmetry integrated region growing segmentation of the brain images using the symmetry affinity matrix, and candidate asymmetric regions are initially extracted using kurtosis and skewness of symmetry affinity matrix. An expectation maximum classifier with Gaussian mixture model is used explicitly to classify asymmetric regions into injury and non-injury. Experimental results are carried out to demonstrate the efficacy of the approach for injury detection. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICIP.2009.5414064 | ICIP |
Keywords | Field | DocType |
injury detection,gaussian mixture model,candidate asymmetric region,asymmetric region,new brain injury detection,expectation-maximisation algorithm,brain image segmentation,symmetry-integrated injury detection,kurtosis,symmetry integrated region,brain image,asymmetric region classification,image segmentation,injuries,brain mri,expectation maximum classifier,magnetic resonance imaging,feature extraction,image classification,biomedical mri,gaussian processes,brain,segmentation,symmetry affinity matrix,skewness,2d anatomical brain structure,symmetry,medical image processing,symmetry affinity,region growing,data mining,decision support systems,magnetic resonance image,brain imaging | Computer vision,Pattern recognition,Computer science,Segmentation,Image segmentation,Artificial intelligence,Region growing,Gaussian process,Contextual image classification,Asymmetry,Mixture model,Kurtosis | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4244-5655-0 | 978-1-4244-5655-0 | 3 |
PageRank | References | Authors |
0.45 | 5 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yu Sun | 1 | 8 | 1.18 |
| Bir Bhanu | 2 | 3356 | 380.19 |
| Shiv Bhanu | 3 | 3 | 0.45 |