The Community for Technology Leaders
2011 24th International Symposium on Computer-Based Medical Systems (CBMS) (2011)
Bristol
June 27, 2011 to June 30, 2011
ISBN: 978-1-4577-1189-3
pp: 1-6
F. E. C. Atho , Comput. Sci. Dept., Univ. of Sao Paulo, Sao Carlos, Brazil
A. J. M. Traina , Comput. Sci. Dept., Univ. of Sao Paulo, Sao Carlos, Brazil
C. Traina , Comput. Sci. Dept., Univ. of Sao Paulo, Sao Carlos, Brazil
P. R. B. Diniz , Med. Sch. of Ribeirao Preto, Univ. of Sao Paulo, Ribeira~o Preto, Brazil
Antonio C. dos Santos , Med. Sch. of Ribeirao Preto, Univ. of Sao Paulo, Ribeira~o Preto, Brazil
ABSTRACT
This work presents a new segmentation model called Similarity Cloud Model (SCM) based on hippocampus feature extraction. The segmentation process is divided in two main operations: localization by similarity and cloud adjustment. The first process uses the cloud to localize the most probable position of the hippocampus in a target volume. Segmentation is completed by a reformulation of the cloud to correct the final labeling, based on a new computation of arc-weights. This method has been tested in an entire dataset of 235 MRI combining healthy and epileptic patients. Results indicate superior quality segmentation in comparison with similar graph and bayesian-based models.
INDEX TERMS
Bayesian-based models, similarity cloud model, hippocampus segmentation technique, hippocampus feature extraction, localization, cloud adjustment, MRI, healthy patients, epileptic patients
CITATION

C. Traina, A. J. Traina, F. E. Atho, P. R. Diniz and A. C. dos Santos, "The Similarity Cloud Model: A novel and efficient hippocampus segmentation technique," 2011 24th International Symposium on Computer-Based Medical Systems (CBMS), Bristol, 2011, pp. 1-6.
doi:10.1109/CBMS.2011.5999148
99 ms
(Ver 3.3 (11022016))