Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Multi-View Based Computer Aided Diagnosis in Digital Mammography

디지털 유방영상에서 멀티영상 기반의 컴퓨터 보조 진단에 관한 연구

  • Choi, Hyoung-Sik (Department of Biomedical Engineering, Hanyang University) ;
  • Cho, Yong-Ho (Department of Biomedical Engineering, Hanyang University) ;
  • Cho, Baek-Hwan (Department of Biomedical Engineering, Hanyang University) ;
  • Moon, Woo-Kyoung (Department of Diagnostic Radiology, College of Medicine, Seoul National University) ;
  • Im, Jung-Gi (Department of Diagnostic Radiology, College of Medicine, Seoul National University) ;
  • Kim, In-Young (Department of Biomedical Engineering, Hanyang University) ;
  • Kim, Sun-I. (Department of Biomedical Engineering, Hanyang University)
  • 최형식 (한양대학교 의용생체공학과) ;
  • 조용호 (한양대학교 의용생체공학과) ;
  • 조백환 (한양대학교 의용생체공학과) ;
  • 문우경 (서울대학교 의과대학 진단방사선과) ;
  • 임정기 (서울대학교 의과대학 진단방사선과) ;
  • 김인영 (한양대학교 의용생체공학과) ;
  • 김선일 (한양대학교 의용생체공학과)
  • Published : 2007.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

For the past decade, the full-field digital mammography has been widely used for early diagnosis of breast cancer, and computer aided diagnosis has been developed to assist physicians as a second opinion. In this study, we try to predict the breast cancer using both mediolateral oblique(MLO) view and craniocaudal(CC) view together. A skilled radiologist selected 35 pairs of ROIs from both MLO view and CC view of digital mammogram. We extracted textural features using Spatial Grey Level Dependence matrix from each mammogram and evaluated the generalization performance of the classifier using Support Vector Machine. We compared the multi-view based classifier to single-view based classifier that is built from each mammogram view. The results represent that the multi-view based computer aided diagnosis in digital mammogram could improve the diagnostic performance and have good possibility for clinical use to assist physicians as a second opinion.

Keywords

References

  1. D. B. Kopans, Breast Imaging: Lippincott Williams & Wilkins, 1997
  2. S. H. Heywang-Kobrunner, Diagnostic Breast Imaging: Thieme, 1997
  3. E. Alberdi, R. Lee, and P. Taylor, 'Radiologists' description and interpretation of mammographic microcalcifications: A knowledge elicitation study for computerized decision support,' presented at IWDM, Toronto, Canada, 2000
  4. R. M. Nishikawa, M. L. Giger, K. Doi, C. J. Vyboryny, and R. A. Schmidt, 'Computer aided detection of clustered microcalcifications on digital mammograms,' Medical and Biological Engineering & Computing, vol. 33, pp. 174-178, 1995 https://doi.org/10.1007/BF02523037
  5. W. Veldkamp, N. Karssemeijer, J. Otten, and J. Hendriks, 'Automated classification of clustered microcalcifications into malignant and benign types,' Medical Physics, vol. 27, pp. 2600-2608, 2000 https://doi.org/10.1118/1.1318221
  6. M. Kallergi, 'Computer aided diagnosis of mammographic microcalfication clusters,' Medical Physics, vol. 31, pp. 314-326, 2004 https://doi.org/10.1118/1.1637972
  7. A. Petrosian, H. P. Chan, M. A. Helvie, M. M. Goodsitt, and D. D. Adler, 'Computer-aided diagnosis in mammography: classification of mass and normal tissue by texture analysis,' Phys. Med. BIol., vol. 39, pp. 2273-2288, 1994 https://doi.org/10.1088/0031-9155/39/12/010
  8. H. P. Chan, Sahiner B., W. L. Lam, N. Petrick, M. A. Helvie, M. M. Goodsitt, and D. D. Adler, 'Computerized analysis of mammographic microcalcifications in morphological and texture feature spaces,' Medical Physics, vol. 25, pp. 2007-2019, 1998 https://doi.org/10.1118/1.598389
  9. E. Thurfjell, 'Mammography screening: One versus two views and independent double reading,' Acta Radiologica, vol. 35, pp. 340- 344, 1994 https://doi.org/10.1177/028418519403500406
  10. E. Thurfjell, A. Taube, and L. Tabar, 'One- versus two-view mamm- ography screening: A prospective population-based study,' Acta Radiologica, vol. 35, pp. 340-344, 1994 https://doi.org/10.1177/028418519403500406
  11. A. Tiedeu, C. Daul, P. Graebling, and D. Wolf, 'Correspondence between microcalcification projections on two mammographic views acquired with digital systems,' Comp. Med. Imag. and Graph, vol. 28, pp. 151-158, 2005
  12. Z. Huo, M. L. Giger, D. E. Wolverton, W. Zhong, and S. Cumming, 'Computerized analysis of mammographic parenchymal patterns for breast cancer risk assessment: Feature selection,' Medical Physics, vol. 27, pp. 4-12, 2000 https://doi.org/10.1118/1.598851
  13. R. M. Haralick, K. Shanmugam, and I. Dinstein, 'Textural features for image classification,' IEEE Trans on Systems, Man, Cybernetics, vol. SMC-3, pp. 610-621, 1973 https://doi.org/10.1109/TSMC.1973.4309314
  14. V. Vapnik, The nature of statistical learning theory, New York: Springer, 1995
  15. C. J. C. Burges, 'A tutorial on support vector machines for pattern recognition,' Data Mining and Knowledge Discovery, vol. 2, pp. 121-167, 1998 https://doi.org/10.1023/A:1009715923555
  16. N. Cristianini and J. Shawe-Taylor, An introduction to support vector machines and other kernel-based learning methods, Cambridge, UK: Cambridge University Press, 2000
  17. C.C. Chang and C.J. Lin, 'LIBSVM : a library for support vector machines,' Software available at http://www.csie.ntu.edu.tw/ ~cjlin/libsvm 2001
  18. I. Guyon and A. Elisseeff, 'An introduction to variable and feature selection,' J Mach Learn Res, vol. 3, pp. 1157-1182, 2003 https://doi.org/10.1162/153244303322753616
  19. M. Hall, 'Correlation-based feature selection for discrete and numeric class machine learning,' presented at International Conference on Machine Learning, Stanford University, 2000