Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis

Huihua Kenny Chiang; Chui Mei Tiu; Guo Shian Hung; Shiao Chi Wu; Tiffany Y. Chang; Yi Hong Chou

doi:10.1109/ULTSYM.2001.991959

Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis

Huihua Kenny Chiang^*, Chui Mei Tiu, Guo Shian Hung, Shiao Chi Wu, Tiffany Y. Chang, Yi Hong Chou

^*此作品的通信作者

研究成果: Conference article › 同行評審

10 引文斯高帕斯（Scopus）

摘要

To assist the ultrasound (US) diagnosis of solid breast tumors by using stepwise logistic regression (SLR) analysis of tumor contour features, we reviewed 111 digitized US images of breast tumors. They were 40 benign breast tumors (fibroadenomas), and 71 infiltrative ductal carcinomas. The contour features were calculated by the radial length. A SLR model with contour features was used to classify tumors as benign or malignant. The accuracy of our model with contour features for classifying malignancies was 91.0% (101 of 111 tumors), the sensitivity was 97.2% (69 of 71), the specificity was 80.0% (32 of 40).

原文	English
頁（從 - 到）	1303-1306
頁數	4
期刊	Proceedings of the IEEE Ultrasonics Symposium
卷	2
DOIs	https://doi.org/10.1109/ULTSYM.2001.991959
出版狀態	Published - 10月 2001
事件	2001 Ultrasonics Symposium - Atlanta, GA, 美國持續時間: 6 10月 2001 → 10 10月 2001

存取文件

10.1109/ULTSYM.2001.991959

其它文件與鏈接

Link to publication in Scopus

引用此

@article{71710d109baa4fd5a739f9d663296daf,

title = "Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis",

abstract = "To assist the ultrasound (US) diagnosis of solid breast tumors by using stepwise logistic regression (SLR) analysis of tumor contour features, we reviewed 111 digitized US images of breast tumors. They were 40 benign breast tumors (fibroadenomas), and 71 infiltrative ductal carcinomas. The contour features were calculated by the radial length. A SLR model with contour features was used to classify tumors as benign or malignant. The accuracy of our model with contour features for classifying malignancies was 91.0% (101 of 111 tumors), the sensitivity was 97.2% (69 of 71), the specificity was 80.0% (32 of 40).",

author = "Chiang, {Huihua Kenny} and Tiu, {Chui Mei} and Hung, {Guo Shian} and Wu, {Shiao Chi} and Chang, {Tiffany Y.} and Chou, {Yi Hong}",

year = "2001",

month = oct,

doi = "10.1109/ULTSYM.2001.991959",

language = "English",

volume = "2",

pages = "1303--1306",

journal = "Proceedings of the IEEE Ultrasonics Symposium",

issn = "1051-0117",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2001 Ultrasonics Symposium ; Conference date: 06-10-2001 Through 10-10-2001",

}

TY - JOUR

T1 - Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis

AU - Chiang, Huihua Kenny

AU - Tiu, Chui Mei

AU - Hung, Guo Shian

AU - Wu, Shiao Chi

AU - Chang, Tiffany Y.

AU - Chou, Yi Hong

PY - 2001/10

Y1 - 2001/10

N2 - To assist the ultrasound (US) diagnosis of solid breast tumors by using stepwise logistic regression (SLR) analysis of tumor contour features, we reviewed 111 digitized US images of breast tumors. They were 40 benign breast tumors (fibroadenomas), and 71 infiltrative ductal carcinomas. The contour features were calculated by the radial length. A SLR model with contour features was used to classify tumors as benign or malignant. The accuracy of our model with contour features for classifying malignancies was 91.0% (101 of 111 tumors), the sensitivity was 97.2% (69 of 71), the specificity was 80.0% (32 of 40).

AB - To assist the ultrasound (US) diagnosis of solid breast tumors by using stepwise logistic regression (SLR) analysis of tumor contour features, we reviewed 111 digitized US images of breast tumors. They were 40 benign breast tumors (fibroadenomas), and 71 infiltrative ductal carcinomas. The contour features were calculated by the radial length. A SLR model with contour features was used to classify tumors as benign or malignant. The accuracy of our model with contour features for classifying malignancies was 91.0% (101 of 111 tumors), the sensitivity was 97.2% (69 of 71), the specificity was 80.0% (32 of 40).

UR - http://www.scopus.com/inward/record.url?scp=0035729850&partnerID=8YFLogxK

U2 - 10.1109/ULTSYM.2001.991959

DO - 10.1109/ULTSYM.2001.991959

M3 - Conference article

AN - SCOPUS:0035729850

SN - 1051-0117

VL - 2

SP - 1303

EP - 1306

JO - Proceedings of the IEEE Ultrasonics Symposium

JF - Proceedings of the IEEE Ultrasonics Symposium

T2 - 2001 Ultrasonics Symposium

Y2 - 6 October 2001 through 10 October 2001

ER -

Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis

摘要

存取文件

其它文件與鏈接

指紋

引用此