MS plaque segmentation using masking clustering and level set method
| Autor: | Nalan Ozkurt, Suleyman Men, Hasan Ozyavru |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Masking (art)
Level set (data structures) Level set method Fuzzy clustering medicine.diagnostic_test Computer science business.industry Multiple sclerosis Magnetic resonance imaging Image segmentation Corpus callosum medicine.disease White matter medicine.anatomical_structure Level set medicine Segmentation Computer vision Artificial intelligence Cluster analysis business |
| Zdroj: | SIU |
| DOI: | 10.1109/siu.2012.6204478 |
| Popis: | In this study, a series of methods with some contributions have been proposed in order to segment brain tissues affected by the multiple sclerosis (MS). Since MS disease usually occurs in white matter of the brain and noting that corpus callosum is the largest white matter structure in the brain, filtering out the parts of corpus callosum that are not affected by disease helps improve segmentation. Magnetic resonance dual T1 – T2 images of the brain is used for masking corpus callosum. Since the pixel by pixel multiplication of T1 – T2 images is possible with dual MR Imaging and the outcome serves for the pupose of masking, the multiplication is used as preprocessing tool. Standart fuzzy clustering algorithm is used to find out the cluster centers. The speed term for the level set method is defined based on the cluster centers. Thus any part of affected tissue that is pointed by radiologist is segmented up to the connected borders by use of Level Set Method. The outcome of this study may help radiologist to track and record the progress of the disease as it might be more time consuming otherwise. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|