Title :
Validity guided clustering for brain tumor segmentation [treatment planning]
Author :
Velthuizen, R.P.
Author_Institution :
Dept. of Radiology, Univ. of South Florida, Tampa, FL, USA
Abstract :
Clustering of MRI for unsupervised tumor volume segmentation often fails to identify pathological tissues. In this paper, a refinement of fuzzy c-means segmentation is proposed using a validity measure. The method is applied to three patient cases with different tumor types. A significant improvement compared to FCM is achieved for two tumor types, both in the detection of the tumor and the accuracy of the pixel assignments
Keywords :
biomedical NMR; brain; image recognition; image segmentation; medical image processing; radiation therapy; surgery; MRI; brain tumor segmentation; fuzzy c-means segmentation; pathological tissues; patient cases; pixel assignment accuracy; treatment planning; tumor detection; tumor types; unsupervised tumor volume segmentation; validity guided clustering; validity measure; Educational institutions; Extraterrestrial measurements; Fuzzy logic; Image segmentation; Internet; Lesions; Magnetic resonance imaging; Neoplasms; Radiology; Size measurement;
Conference_Titel :
Engineering in Medicine and Biology Society, 1995., IEEE 17th Annual Conference
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-2475-7
DOI :
10.1109/IEMBS.1995.575176
