Abstract
We evaluated a series of pathologically proven breast tumors using the support vector
machine (SVM) in the differential diagnosis of solid breast tumors. This study evaluated
two ultrasonic image databases, i.e., DB1 and DB2. The DB1 contained 140 ultrasonic
images of solid breast nodules (52 malignant and 88 benign). The DB2 contained 250
ultrasonic images of solid breast nodules (35 malignant and 215 benign). The physician-located
regions of interest (ROI) of sonography and textual features were utilized to classify
breast tumors. An SVM classifier using interpixel textual features classified the
tumor as benign or malignant. The receiver operating characteristic (ROC) area index
for the proposed system on the DB1 and the DB2 are 0.9695±0.0150 and 0.9552±0.0161,
respectively. The proposed system differentiates solid breast nodules with a relatively
high accuracy and helps inexperienced operators avoid misdiagnosis. The main advantage
in the proposed system is that the training procedure of SVM was very fast and stable.
The training and diagnosis procedure of the proposed system is almost 700 times faster
than that of multilayer perception neural networks (MLPs). With the growth of the
database, new ultrasonic images can be collected and used as reference cases while
performing diagnoses. This study reduces the training and diagnosis time dramatically.
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
- Letter from the editor.Semin Ultrasound CT MR. 2000; 21: 285
- Solid breast nodules: use of sonography to distinguish between benign and malignant lesions.Radiology. 1995; 196: 123-134
- The prevalence of carcinoma in palpable vs impalpable, mammographically detected lesions.AJR Am J Roentgenol. 1991; 157: 21-24
- Clinically occult breast lesions: localization and significance.Radiology. 1987; 162: 167-170
- Prebiopsy localization of nonpalpable breast lesions.AJR Am J Roentgenol. 1984; 143: 477-481
- Breast cancer diagnosis using self-organizing map for sonography.Ultrasound Med Biol. 2000; 26: 405-411
- Texture analysis of breast tumors on sonograms.Semin Ultrasound CT MR. 2000; 21: 308-316
- Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks.Ultrasound Med Biol. 2002; 28: 1301-1310
- Computer-aided diagnosis applied to US of solid breast nodules by using neural networks.Radiology. 1999; 213: 407-412
- Data mining with decision trees for diagnosis of breast tumor in medical ultrasonic images.Breast Cancer Res Treat. 2001; 66: 51-57
- Statistical learning theory. Wiley, New York1998
- An introduction to support vector machines and other kernel-based learning methods. Cambridge Univ. Press, United Kingdom2000
- A support vector machine approach for detection of microcalcifications.IEEE Trans Med Imaging. 2002; 21: 1552-1563
Yang MH, Roth D, Ahuja N. A tale of two classifiers: SNoW vs. SVM in visual recognition. Comput Vis—Eccv 2002 Pt Iv 2002;2353:685–699.
- Support vector machines for texture classification.IEEE Trans Pattern Anal Mach Intell. 2002; 24: 1542-1550
- Identifying splicing sites in eukaryotic RNA: support vector machine approach.Comput Biol Med. 2003; 33: 17-29
- Prediction of protein retention times in anion-exchange chromatography systems using support vector regression.J Chem Inf Comput Sci. 2002; 42: 1347-1357
- Robust support vector machine with bullet hole image classification.IEEE Trans Syst Man Cybern, Part C Appl Rev. 2002; 32: 440-448
Article info
Publication history
Published online: December 21, 2004
Received in revised form:
July 20,
2004
Received:
May 10,
2004
Identification
Copyright
© 2005 Elsevier Inc. Published by Elsevier Inc. All rights reserved.
