Breast tumor classification based on serial grayscale ultrasound images / 中国医疗器械杂志
Chinese Journal of Medical Instrumentation
; (6): 186-189, 2008.
Article
in Zh
| WPRIM
| ID: wpr-309617
Responsible library:
WPRO
ABSTRACT
This paper proposes an algorithm of evaluating the compression depth, and then to extract four normalized mammary elasticity characteristic parameters with respect to the compression depth. The classification experiments show that these elasticity parameters have a good capability in determining whether the tumor is benign or malignant, and if combined with morphological parameters, the accuracy, sensitivity and specificity can be improved and increased to 95.19%, 98.82% and 92.16%, respectively.
Full text:
1
Database:
WPRIM
Main subject:
Algorithms
/
Breast Neoplasms
/
Diagnostic Imaging
/
Ultrasonography, Mammary
/
Sensitivity and Specificity
/
Elasticity Imaging Techniques
/
Methods
Type of study:
Diagnostic_studies
Limits:
Female
/
Humans
Language:
Zh
Journal:
Chinese Journal of Medical Instrumentation
Year:
2008
Document type:
Article