Cell-based graph cut for segmentation of 2D/3D sonographic breast images

Boundary delineation is the fundamental basis of many sonographic image analyses. In sonographic breast lesion images, it's complicated and time consuming for physicians to delineate the lesion boundaries. When it comes to three dimensional sonographic breast lesions image, delineation of lesio...

Full description

Saved in:
Bibliographic Details
Main Authors: Hsin-Hung Chiang, Jie-Zhi Cheng, Pei-Kai Hung, Chun-You Liu, Cheng-Hong Chung, Chung-Ming Chen
Format: Conference Proceeding
Language:English
Subjects:
Breast
Cell Competition
Cost function
Graph Cut
Image edge detection
Image segmentation
Lesions
Partitioning algorithms
Sonogram
Sonographic Image
Speckle
Ultrasonic imaging
Ultrasonography
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Boundary delineation is the fundamental basis of many sonographic image analyses. In sonographic breast lesion images, it's complicated and time consuming for physicians to delineate the lesion boundaries. When it comes to three dimensional sonographic breast lesions image, delineation of lesion boundary becomes much more complicated. Taking advantage of cell competition algorithm along with its good region structure, generated cells can be served as elegant nodes for graph cut. Further, a similar weight function plays an important role in the estimation of lesion boundary to avoid visible weak edge and isolated node in graph cut. The integration of cell competition and graph cut can be intuitively implemented in three dimensional images, in addition to the reduction of computational time. With efficiency and accuracy of lesion detection, a computer aided system was therefore developed to fulfill clinical applications.
ISSN:1945-7928
1945-8452
DOI:10.1109/ISBI.2010.5490384