An enhanced fuzzy c-means medical segmentation algorithm
Fuzzy-based algorithms have been widely used for medical segmentation. Fuzzy c-means (FCM) is one of the popular algorithms which is being used in this field. However this method of segmentation suffers mainly from two issues. Firstly, noisy images highly reduce the quality of segmentation. Secondly...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2015
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/59141/ http://dx.doi.org/10.1109/ISBAST.2014.7013136 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Fuzzy-based algorithms have been widely used for medical segmentation. Fuzzy c-means (FCM) is one of the popular algorithms which is being used in this field. However this method of segmentation suffers mainly from two issues. Firstly, noisy images highly reduce the quality of segmentation. Secondly, the edges of the segmented images are not sharp and clear. Therefore the boundary between the two regions cannot clearly be identified. Our goal of this research is to propose a segmentation algorithm that cancels the negative noise effect on the final result and performs the segmentation with high edge accuracy by combining Sobel edge detection with FCM. Our algorithm is evaluated against three brain magnetic resonance image (MRI) datasets of real patients. The obtained analysis indicates that the edges of the segmented images by our method are sharp and accurate. |
|---|