Paper Info
Title
Multiobjective evolutionary optimization for tumor segmentation of breast ultrasound images.
Abstract
This paper proposes a robust multiobjective evolutionary algorithm (MOEA) to optimize parameters of tumor segmentation for ultrasound breast images. The proposed algorithm employs efficient schemes for reinforcing proximity to Pareto-optimal and diversity of solutions. They are designed to solve multiobjective problems for segmentation accuracy and speed. First objective is evaluated by difference between the segmented outline and ground truth. Second objective is evaluated by elapsed time during segmentation process. The experimental results show the effectiveness of the proposed algorithm compared with conventional MOEA from the viewpoint of proximity to the Pareto-optimal front (improved by 16.4% and 12.4%). Moreover, segmentation results of proposed algorithm describe faster segmentation speed (1.97 second) and higher accuracy (8% Jaccard).
Year
DOI
Venue
2013
10.1109/EMBC.2013.6610334
EMBC
Keywords
Field
DocType
evolutionary computation,pareto-optimal front,image segmentation,biomedical ultrasonics,breast ultrasound images,tumor segmentation,moea,pareto optimisation,robust multiobjective evolutionary optimization,tumours,biological organs,medical image processing,statistics,sociology,measurement
Computer vision,Scale-space segmentation,Evolutionary algorithm,Segmentation,Computer science,Evolutionary computation,Segmentation-based object categorization,Image segmentation,Ground truth,Jaccard index,Artificial intelligence
Conference
Volume
ISSN
Citations 
2013
1557-170X
1
PageRank 
References 
Authors
0.35
11
7
Name
Order
Citations
PageRank
Ye-Hoon Kim11719.78
Baek Hwan Cho2848.71
Yeong Kyeong Seong3226.38
Moon Ho Park410.35
Junghoe Kim510.69
Sinsang Yu610.35
Kyoung-Gu Woo79710.37