摘要
Infiltrative nature is a unique characteristic of breast cancer. Cross-sectional view of infiltrative nature can find a rough lesion contour on ultrasound image. Roughness description is crucial for clinical diagnosis of breast lesions. Based on boundary tracking, traditional roughness descriptors usually suffer from information loss due to dimension reduction. In this paper, a novel 2-D wavelet-based energy feature is proposed for breast lesion classification on ultrasound images. This approach characterizes the roughness of breast lesion contour with normalized spatial frequency components. Feature efficacies are evaluated by using two breast sonogram datasets with lesion contour delineated by an experienced physician and the ImageJ, respectively. Experimental results show that the new feature can obtain excellent performance and robust contour variation resistance.
| 原文 | English |
|---|---|
| 主出版物標題 | The Era of Interactive Media |
| 發行者 | Springer New York |
| 頁面 | 303-312 |
| 頁數 | 10 |
| 卷 | 9781461435013 |
| ISBN（電子） | 9781461435013 |
| ISBN（列印） | 1461435005, 9781461435006 |
| DOIs | |
| 出版狀態 | Published - 2013 十月 1 |
指紋
All Science Journal Classification (ASJC) codes
- Computer Science(all)
引用此文
}
A novel 2D wavelet level energy for breast lesion classification on ultrasound images. / Liao, Yueh Ching; Hung, King Chu; Guo, Shu-Mei; Wang, Po Chin; Yang, Tsung Lung.
The Era of Interactive Media. 卷 9781461435013 Springer New York, 2013. p. 303-312.研究成果: Chapter
TY - CHAP
T1 - A novel 2D wavelet level energy for breast lesion classification on ultrasound images
AU - Liao, Yueh Ching
AU - Hung, King Chu
AU - Guo, Shu-Mei
AU - Wang, Po Chin
AU - Yang, Tsung Lung
PY - 2013/10/1
Y1 - 2013/10/1
N2 - Infiltrative nature is a unique characteristic of breast cancer. Cross-sectional view of infiltrative nature can find a rough lesion contour on ultrasound image. Roughness description is crucial for clinical diagnosis of breast lesions. Based on boundary tracking, traditional roughness descriptors usually suffer from information loss due to dimension reduction. In this paper, a novel 2-D wavelet-based energy feature is proposed for breast lesion classification on ultrasound images. This approach characterizes the roughness of breast lesion contour with normalized spatial frequency components. Feature efficacies are evaluated by using two breast sonogram datasets with lesion contour delineated by an experienced physician and the ImageJ, respectively. Experimental results show that the new feature can obtain excellent performance and robust contour variation resistance.
AB - Infiltrative nature is a unique characteristic of breast cancer. Cross-sectional view of infiltrative nature can find a rough lesion contour on ultrasound image. Roughness description is crucial for clinical diagnosis of breast lesions. Based on boundary tracking, traditional roughness descriptors usually suffer from information loss due to dimension reduction. In this paper, a novel 2-D wavelet-based energy feature is proposed for breast lesion classification on ultrasound images. This approach characterizes the roughness of breast lesion contour with normalized spatial frequency components. Feature efficacies are evaluated by using two breast sonogram datasets with lesion contour delineated by an experienced physician and the ImageJ, respectively. Experimental results show that the new feature can obtain excellent performance and robust contour variation resistance.
UR - http://www.scopus.com/inward/record.url?scp=84929547487&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84929547487&partnerID=8YFLogxK
U2 - 10.1007/978-1-4614-3501-3_25
DO - 10.1007/978-1-4614-3501-3_25
M3 - Chapter
AN - SCOPUS:84929547487
SN - 1461435005
SN - 9781461435006
VL - 9781461435013
SP - 303
EP - 312
BT - The Era of Interactive Media
PB - Springer New York
ER -