Computer-aided Diagnosis of Breast Cancer by Hybrid Fusion of Ultrasound and Mammogram Features

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 325)

Abstract

Ultrasound images are increasingly being used as an important adjunct to X-ray mammograms for diagnosis of breast cancer. In this paper, a computer-aided diagnosis system that utilizes a hybrid fusion strategy based on canonical correlation analysis (CCA) is proposed for discriminating benign and malignant masses. The system combines information from three different sources, i.e., ultrasound and two views of mammogram, namely, mediolateral oblique (MLO) and craniocaudal (CC) views. CCA is employed on ultrasound-MLO and ultrasound-CC feature pairs to explore the hidden correlations between ultrasound and mammographic view. The two pairs of canonical variates are fused at the feature level and given as input to support vector machine (SVM) classifiers. Finally, decisions of the two classifiers are fused. Results show that the proposed system outperforms unimodal systems and state-of-the-art fusion strategies.

Keywords

Breast cancer Canonical correlation analysis Computer-aided diagnosis Hybrid fusion Mammogram Ultrasound 

References

  1. 1.
    N.H. Eltonsy, G.D. Tourassi, A.S. Elmaghraby, A concentric morphology model for the detection of masses in mammography. IEEE Trans. Med. Imag. 2, 880–889 (2007)CrossRefGoogle Scholar
  2. 2.
    S. Malur, S. Wurdinger, A. Moritz, W. Michels, A. Schneider, Comparison of written reports of mammography, sonography and magnetic resonance mammography for preoperative evaluation of breast lesions, with special emphasis on magnetic resonance mammography. Breast Cancer Res. 3, 55–60 (2001)CrossRefGoogle Scholar
  3. 3.
    K. Horsch, M.L. Giger, C.J. Vyborny, L. Lan, E.B. Mendelson, R.E. Hendrick, Classification of breast lesions with multimodality computer-aided diagnosis. observer study results on an independent clinical data set. Radiology 240, 357–368 (2006)CrossRefGoogle Scholar
  4. 4.
    J.L. Jesneck, J.Y. Lo, J.A. Baker, Breast mass lesions: computer-aided diagnosis models with mammographic and sonographic descriptors. Radiology 244, 390–398 (2007)CrossRefGoogle Scholar
  5. 5.
    J.L. Jesneck, L.W. Nolte, J.A. Baker, C.E. Floyd, J.Y. Lo, Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis, Med. Phys. 33, 2945–2954 (2006) http://www.ncbi.nlm.nih.gov/pubmed/16964873
  6. 6.
    P.K. Atrey, M.A. Hossain, A. El-Saddik, M.S. Kankanhalli, Multimodal fusion for multimedia analysis: a survey. Multimedia Syst. 1, 345–379 (2010)CrossRefGoogle Scholar
  7. 7.
    H. Hotelling, Relations between two sets of variates. Biometrika 28, 321–377 (1936)CrossRefMATHGoogle Scholar
  8. 8.
    K. Hu, X. Gao, F. Li, Detection of suspicious lesions by adaptive thresholding based on multiresolution analysis in mammograms. IEEE Trans. Instrum. Meas. 60, 462–472 (2011) http://www.informatik.uni-trier.de/~ley/db/indices/a-tree/l/Li:Fei.html
  9. 9.
    A. Mencattini, M. Salmeri, Metrological characterization of a CADx system for the classification of breast masses in mammograms. IEEE Trans. Instrum. Meas. 59, 2792–2799 (2010)CrossRefGoogle Scholar
  10. 10.
    T.F. Chan, L.A. Vese, Active contours without edges. IEEE Trans. Image Process. 10, 266–277 (2001)CrossRefMATHGoogle Scholar
  11. 11.
    W.C. Shen, R.F. Chang, W.K. Moon, Y.H. Chou, C.S. Huang, Breast ultrasound computer-aided diagnosis using bi-rads features. Acad. Radiol. 14, 928–939 (2007)CrossRefGoogle Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.Department of Electronics and Communication Engineering, Amrita School of EngineeringAmrita Vishwa Vidyapeetham UniversityCoimbatoreIndia
  2. 2.Department of Computer Science and EngineeringCoimbatore Institute of Engineering and TechnologyCoimbatoreIndia

Personalised recommendations