Document Detail


A self-learning segmentation framework--the Taguchi approach.
MedLine Citation:
PMID:  10940606     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
The detection of object boundary is an interesting and challenging task in computer vision and medical image processing. The active contour model (snake model) has attracted much attention for object boundary detection in the past decade. However, due to the lack of understanding on the effect of different energy terms to the behavior of related objective functions for an image, the assignment of weights for different energy terms in this model is usually fulfilled empirically. Few discussions have been brought out specifically for assigning these weights automatically. In this paper, a novel self-learning segmentation framework, based on the snake model is proposed and applied to the detection of cardiac boundaries from ultrasonic images. The framework consists of a learning section and a detection section, and provides a training mechanism to obtain the weights from a desired object contour given manually. This mechanism first employs Taguchi's method to determine the weight ratios among distinct energy terms, followed by a weight refinement step with a genetic algorithm. The refined weights can be treated as the a priori knowledge embedded in the manually defined contour and be used for subsequent contour detection. Experiments with both synthetic and real echocardiac images were conducted with satisfactory outcomes. Results also show that the present method can be used to analyze successive images of the same object with only one training contour. Finally, the validity of the weight determining process was verified by the analysis of variance method (ANOVA).
Authors:
D H Chen; Y N Sun
Related Documents :
9735536 - Recovery of 3d volume from 2-tone images of novel objects.
18625296 - The creation of geometric three-dimensional models of the inner ear based on micro comp...
4067646 - An image processing method for feature extraction of space-occupying lesions.
16579376 - Multiple contour extraction from graylevel images using an artificial neural network.
16003426 - The use of digital imaging for colour matching and communication in restorative dentistry.
18619876 - Microtesla mri of the human brain combined with meg.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society     Volume:  24     ISSN:  0895-6111     ISO Abbreviation:  Comput Med Imaging Graph     Publication Date:    2000 Sep-Oct
Date Detail:
Created Date:  2000-11-01     Completed Date:  2000-11-01     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  8806104     Medline TA:  Comput Med Imaging Graph     Country:  UNITED STATES    
Other Details:
Languages:  eng     Pagination:  283-96     Citation Subset:  IM    
Affiliation:
Department of Computer Science and Information Engineering, National Cheng-Kung University, ROC, Tainan, Taiwan.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Analysis of Variance
Computer Simulation
Echocardiography / methods*
Fuzzy Logic*
Humans
Image Processing, Computer-Assisted*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Fatal acute alcohol intoxication in an ALDH2 heterozygote: a case report.
Next Document:  Digital hand atlas and web-based bone age assessment: system design and implementation.