KMID : 0357520120350030227
|
|
Journal of Radiological Science and Technology 2012 Volume.35 No. 3 p.227 ~ p.235
|
|
Detection Efficiency of Microcalcification using Computer Aided Diagnosis in the Breast Ultrasonography Images
|
|
Lee Jin-Soo
Ko Seong-Jin Kang Se-Sik Kim Jung-Hoon Park Hyung-Hu Choi Seok-Yoon Kim Chang-Soo
|
|
Abstract
|
|
|
Digital Mammography makes it possible to reproduce the entire breast image. And it is used to detect microcalcification and mass which are the most important point of view of nonpalpable early breast cancer, so it has been used as the primary screening test of breast disease. It is reported that microcalcification of breast lesion is important in diagnosis of early breast cancer. In this study, six types of texture features algorithms are used to detect microcalcification on breast US images and the study has analyzed recognition rate of lesion between normal US images and other US images which microcalification is seen. As a result of the experiment, Computer aided diagnosis recognition rate that distinguishes mammography and breast US disease was considerably high 70~98%. The average contrast and entropy parameters were low in ROC analysis, but sensitivity and specificity of four types parameters were over 90%. Therefore it is possible to detect microcalcification on US images. If not only six types of texture features algorithms but also the research of additional parameter algorithm is being continually proceeded and basis of practical use on CAD is being prepared, it can be a important meaning as pre-reading. Also, it is considered very useful things for early diagnosis of breast cancer.
|
|
KEYWORD
|
|
Breast US, Microcalcification, Texture features algorithms, ROC analysis
|
|
FullTexts / Linksout information
|
|
|
|
Listed journal information
|
|
|