Share Email Print

Journal of Electronic Imaging

Partial dependence of breast tumor malignancy on ultrasound image features derived from boosted trees
Author(s): Wei Yang; Su Zhang; Wenying Li; Yaqing Chen; Hongtao Lu; Wufan Chen; Yazhu Chen
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Various computerized features extracted from breast ultrasound images are useful in assessing the malignancy of breast tumors. However, the underlying relationship between the computerized features and tumor malignancy may not be linear in nature. We use the decision tree ensemble trained by the cost-sensitive boosting algorithm to approximate the target function for malignancy assessment and to reflect this relationship qualitatively. Partial dependence plots are employed to explore and visualize the effect of features on the output of the decision tree ensemble. In the experiments, 31 image features are extracted to quantify the sonographic characteristics of breast tumors. Patient age is used as an external feature because of its high clinical importance. The area under the receiver-operating characteristic curve of the tree ensembles can reach 0.95 with sensitivity of 0.95 (61/64) at the associated specificity 0.74 (77/104). The partial dependence plots of the four most important features are demonstrated to show the influence of the features on malignancy, and they are in accord with the empirical observations. The results can provide visual and qualitative references on the computerized image features for physicians, and can be useful for enhancing the interpretability of computer-aided diagnosis systems for breast ultrasound.

Paper Details

Date Published: 1 April 2010
PDF: 9 pages
J. Electron. Imag. 19(2) 023004 doi: 10.1117/1.3385763
Published in: Journal of Electronic Imaging Volume 19, Issue 2
Show Author Affiliations
Wei Yang, Shanghai Jiao Tong Univ. (China)
Su Zhang, Shanghai Jiao Tong Univ. (China)
Wenying Li, Shanghai Jiao Tong Univ. (China)
Yaqing Chen, Shanghai Jiao Tong Univ. (China)
Hongtao Lu, Shanghai Jiao Tong Univ. (China)
Wufan Chen, Univ. of Electronic Science and Technology of China (China)
Yazhu Chen, Shanghai Jiao Tong Univ. (China)

© SPIE. Terms of Use
Back to Top