DocumentCode :
2804991
Title :
Cloud bank: A multiple clouds model and its use in MR brain image segmentation
Author :
Miranda, Paulo A V ; Falcão, Alexandre X. ; Udupa, Jayaram K.
Author_Institution :
Inst. of Comput., Univ. of Campinas, Campinas, Brazil
fYear :
2009
fDate :
June 28 2009-July 1 2009
Firstpage :
506
Lastpage :
509
Abstract :
We present improvements to a recently proposed model-based segmentation strategy, called Clouds. We demonstrate the usefulness of the new model Cloud Bank in the automatic MR-image segmentation of the brain (without medulla and spinal cord), the cerebellum, and each brain hemisphere. These structures are connected in several parts, imposing serious challenges for segmentation. The results indicate that the new model is a fast and accurate tool to eliminate user´s intervention or, at least, reduce it to simple corrections, in the context of brain image segmentation.
Keywords :
biomedical MRI; brain models; image segmentation; medical image processing; Cloud Bank; MRI; brain; cerebellum; image segmentation; multiple clouds model; Brain modeling; Cloud computing; Context modeling; Image recognition; Image segmentation; Object recognition; Radiology; Shape; Spinal cord; Uncertainty; MR-image segmentation; graph-cut measures; image foresting transform; medical image processing; model-based and image-based segmentation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2009. ISBI '09. IEEE International Symposium on
Conference_Location :
Boston, MA
ISSN :
1945-7928
Print_ISBN :
978-1-4244-3931-7
Electronic_ISBN :
1945-7928
Type :
conf
DOI :
10.1109/ISBI.2009.5193095
Filename :
5193095
Link To Document :
بازگشت