We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Ganglion Cyst Region Extraction from Ultrasound Images Using Possibilistic C-Means Clustering Method.
- Authors
Suryadibrata, Alethea; Kwang Baek Kim
- Abstract
Ganglion cysts are benign soft tissues usually encountered in the wrist. In this paper, we propose a method to extract a ganglion cyst region from ultrasonography images by using image segmentation. The proposed method using the possibilistic c-means (PCM) clustering method is applicable to ganglion cyst extraction. The methods considered in this thesis are fuzzy stretching, median filter, PCM clustering, and connected component labeling. Fuzzy stretching performs well on ultrasonography images and improves the original image. Median filter reduces the speckle noise without decreasing the image sharpness. PCM clustering is used for categorizing pixels into the given cluster centers. Connected component labeling is used for labeling the objects in an image and extracting the cyst region. Further, PCM clustering is more robust in the case of noisy data, and the proposed method can extract a ganglion cyst area with an accuracy of 80% (16 out of 20 images).
- Subjects
SOFT tissue tumors; ULTRASONIC imaging; IMAGE segmentation; MEDIAN filters (Electronics); CYSTS (Pathology); DIAGNOSIS; THERAPEUTICS
- Publication
Journal of Information & Communication Convergence Engineering, 2017, Vol 15, Issue 1, p49
- ISSN
2234-8255
- Publication type
Article
- DOI
10.6109/jicce.2017.15.1.49