Abstract
Doppler ultrasound imaging provides vascular information that could characterize benign
and malignant breast masses in many previous publications. In this study, we applied
vascular quantification and morphology features derived from three-dimensional power
Doppler ultrasound as classifiers based on support vector machine. An Az value under
the receiver operating characteristic (ROC) curve was used to measure the significance
of each vascularization feature. Sixty solid breast tumors were assessed. According
to the Az value for the ROC curve of the selected features, the classification performance
of the proposed method was 0.8423, indicating that vascular morphologic information
is valuable in the classification of breast lesions.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Clinical ImagingAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Cancer prevention & early detection facts & figures 2009.American Cancer Society, Atlanta, GA2009
- Cancer facts & figures 2009.American Cancer Society, Atlanta, GA2009
- Reduction of breast biopsies with a modified self-organizing map.IEEE Trans Neural Netw. 1997; 8: 1386-1396
- Breast sonography.Breast Dis. 1998; 10: 55-66
- Benign versus malignant solid breast masses: US differentiation.Radiology. 1999; 213: 889-894
- Characterization of benign and malignant solid breast masses in harmonic 3D power Doppler imaging.Eur J Radiol. 2009; 71: 89-95
- Classification of benign and malignant breast tumors using neural networks and three-dimensional power Doppler ultrasound.Ultrasound Obstet Gynecol. 2008; 32: 97-102
- Characterization of benign and malignant solid breast masses: harmonic versus nonharmonic 3D power Doppler imaging.Ultrasound Med Biol. 2009; 35: 353-359
- Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks.Radiology. 2003; 226: 504-514
- Analysis of tumor vascularity using three-dimensional power Doppler ultrasound images.IEEE Trans Med Imaging. 2008; 27: 320-330
- Anatomy and flow in normal and ischemic microvasculature based on a novel temporal fractal dimension analysis algorithm using contrast enhanced ultrasound.IEEE Trans Med Imaging. 2006; 25: 1079-1086
- Computer-supported angiogenesis quantification using image analysis and statistical averaging.IEEE Trans Inf Technol Biomed. 2008; 12: 650-657
- Solid breast masses: neural network analysis of vascular features at three-dimensional power Doppler US for benign or malignant classification.Radiology. 2007; 243: 56-62
- A 3D 12-subiteration thinning algorithm based on P-simple points.Discrete Applied Mathematics. 2004; 139: 171-195
- The meaning and use of the area under a receiver operating characteristic (ROC) curve.Radiology. 1982; 143: 29-36
- Support vector machines for texture classification.IEEE Trans Pattern Anal Mach. Intell. 2002; 24: 1542-1550
- Robust support vector machine with bullet hole image classification.Syst Man Cybern Part C IEEE Trans. 2002; 32: 440-448
- Breast cancer angiogenesis: a quantitative morphologic and Doppler imaging study.Ann Surg Oncol. 1995; 2: 246-251
- Evaluating tumor vascularization with Doppler ultrasound.Radiologe. 1998; 38: 335-343
- Identification of angiogenesis in primary breast carcinoma according to the image analysis.Breast Cancer Res Treat. 2002; 74: 121-129
Article info
Publication history
Published online: December 26, 2011
Accepted:
November 14,
2011
Received:
October 4,
2011
Identification
Copyright
© 2012 Elsevier Inc. Published by Elsevier Inc. All rights reserved.
