Advertisement

Wavelets for Computer-Aided Diagnosis in Radiographic Images

  • Hiroyuki Yoshida
Part of the Computational Imaging and Vision book series (CIVI, volume 19)

Abstract

Computer-vision techniques based on wavelets are presented with applications to computer-aided diagnosis (CAD) in medical images. CAD is a method for assisting radiologists’ interpretation of medical images. CAD schemes act as a second reader and alert radiologists to suspicious lesions. Development of CAD schemes is an active area of research, motivated by the fact that radiologists tend to misdiagnose cancerous lesions in medical images. In the past several years, we have been extensively developing wavelet-based techniques for CAD schemes. Development of these techniques has led to a new CAD scheme and has yielded significant improvements in the performance of the existing CAD schemes. This chapter describes two wavelet-based, low-level computer vision techniques: simultaneous segmentation and registration, and matching pursuit with optimally weighted wavelet packets. We present their application to the computer-aided detection of lung nodules in chest radiographs and microcalcifications in mammograms.

Keywords

Wavelet Coefficient Wavelet Packet Lung Nodule Registration Method Wavelet Domain 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. American Cancer Society (2000). Cancer facts and figures. American Cancer Society.Google Scholar
  2. Anastasio, M. A., Yoshida, H., Nagel, R., Nishikawa, R. M., and Doi, K. (1998). A genetic algorithm-based method for optimizing the performance of a computer-aided diagnosis scheme for detection of clustered microcalcifications in mammograms. Medical Physics, 25:1613–1620.CrossRefGoogle Scholar
  3. Bird, R. G., Wallace, T. W., and Yankaskas, B. C. (1992 Analysis of cancers missed at screening mammography. Radiology, 184:613–617.Google Scholar
  4. Burhenne, H., Burhenne, L., Goldberg, F., Hislop, T., Worth, A. J., Rebbeck, P. M., and Kan, L. (1994). Interval breast cancers in the screening mammography program of british columbia: Analysis and classification. AJR, 162:1067–1071.Google Scholar
  5. Carreira, M. J., Cabello, D., Penedo, M. G., and Pardo, J. M. (1996). Computer-aided lung nodule detection in chest radiography. Lecture Notes in Computer Science, 1024:331–338.CrossRefGoogle Scholar
  6. Casella, G. and Berger, R. L. (1990). Statistical Inference. Duxbury Press, Belmont, California.zbMATHGoogle Scholar
  7. Chan, H.-P., Doi, K. S. G., Vyborny, C. J., MacMahon, H., and Jokich, P. M. (1987) . Image feature analysis and computer-aided diagnosis in digital radiography. 1. Automated detection of microcalcifications in mammography. Med Phys, 14:538–548.CrossRefGoogle Scholar
  8. Coifman, R. R. and Wickerhauser, M. (1994). Adapted waveform analysis as a tool for modelling, feature extraction, and denoising. Optical Engineering, 33:2170–2174.CrossRefGoogle Scholar
  9. Coifman, R. R. and Wickerhauser, M. V. (1992). Entropy-based algorithms for best basis selection. IEEE Trans. Information Theory, 38:1713–1716.CrossRefGoogle Scholar
  10. Daubechies, I. (1992). Ten Lectures on Wavelets. SIAM, Philadelphia, PAzbMATHCrossRefGoogle Scholar
  11. Difazio, M. C., MacMahon, H., Xu, X.-W., Tsai, P., Shiraishi, J., Armato, S. G., and Doi, K. (1997). Digital chest radiography: Effect of temporal subtraction images on detection accuracy. Radiology, 202:447–452.Google Scholar
  12. Doi, K., MacMahon, H., Giger, M., and Hoffmann, K., editors (1999). Compuer-aided diagnosis in medical imaging. Elsevier, Amsterdam.Google Scholar
  13. Efron, E., editor (1982). The jackknife, the bootstrap, and other resampling plans. Society for Industrial and Applied Mathematics, Philadelphia.Google Scholar
  14. Forrest, J. and Friedman, P. (1981). Radiologic errors in patients with lung cancer. West J Med, 134:485–490.Google Scholar
  15. Giger, M., Huo, Z., Kupinski, M. A., and Vyborny, C. J. (2000). Computeraided diagnosis in mammography. In Fitzpatrick, J. M. and Sonka, M., editors, Handbook of Medical Imaging, volume 2, pages 915–1004. The International Society for Optical Engineering.Google Scholar
  16. Giger, M. and MacMahon, H. (1996). Image processing and computeraided diagnosis. In Greenes, R. A. and Bauman, R., editors, Radiologic Clinics of North America, pages 565–596. Saunders Publishing Co.Google Scholar
  17. Heidbreder, G. R., editor (1996). Maximum Entropy and Bayesian Methods. Kluwer Academic Publishers.zbMATHGoogle Scholar
  18. Jiang, Y., Nishikawa, R. M., Wolverton, D. E., Metz, C. E., Giger, M. L., Schmidt, R. A., Vyborny, C. J., and Doi, K. (1996). Malignant and benign clustered microcalcifications: Automated feature analysis and classification. Radiology, 198:671–678.Google Scholar
  19. Kano, A., Doi, K., MacMahon, H., Hassell, D. D., and Giger, M. L. (1994). Digital image subtraction of temporally sequential chest images for detection of interval changes. Med Phys, 21:453–461.CrossRefGoogle Scholar
  20. Keserci, B. and Yoshida, H. (2000). Bayesian wavelet snake model for computer-aided diagnosis of lung nodules in chest radiographs. Medical Image Analysis (accepted).Google Scholar
  21. Kundel, H. L. and Nodine, C. F. (1980). Interpreting chest radiographs without visual search. Radiology, 116:527–532.Google Scholar
  22. Laine, A., Schuler, S., Fan, J., and Huda, W. (1994). Mammographic feature enhancement by multiscale analysis. IEEE Transactions on Medical Imaging, 13:1–28.CrossRefGoogle Scholar
  23. Little, J., Hill, D., and Hawkes, D. (1996). Deformations incorporating rigid structures. In Workshop on Mathematical Methods in Biomedical Image Analysis, Proc IEEE, pages 104–113. IEEE.CrossRefGoogle Scholar
  24. Lo, S., Freedman, M., Lin, J., and Mun, S. (1993). Automatic lung nodule detection using profile matching and back-propagation neural network techniques. Journal of Digital Imaging, 6:48–54.CrossRefGoogle Scholar
  25. Mallat, S. G. and Zhang, Z. (1993). Matching pursuits with time-frequency dictionaries. IEEE Trans. on Signal Processing, 41:3397–3415.zbMATHCrossRefGoogle Scholar
  26. Matsumoto, T., Yoshimura, H., Doi, K., Giger, M. L., Kano, A., MacMahon, H., Abe, K., and Montner, S. (1992). Image feature analysis of false positive diagnoses produced by automated detection of lung nodules. Invest Radiol, 27:587–597.CrossRefGoogle Scholar
  27. Maurer, C. R. and Fitzpatrick, J. M. (1993). A review of medical image registration. In Maciunas, R. J., editor, Interactive Image- Guided Neurosurgery, pages 17–44, Park Ridge, IL. American Association of Neurological Surgeons.Google Scholar
  28. Metz, C. (2000) . Fundamental roc analysis. In Fitzpatrick, J. M. and Sonka, M., editors, Handbook of Medical Imaging, volume 1, pages 751–770. The International Society for Optical Engineering.Google Scholar
  29. Metz, C. E. (1989). Some practical issues of experimental design and data analysis in radiological ROC studies. Invest Radiol, 24:234–245.CrossRefGoogle Scholar
  30. Metz, C. E., Herman, B. A., and Shen, J.-H. (1998). Maximum-likelihood estimation of ROC curves from continuously-distributed data. Statist Med, 17:1033–1053.CrossRefGoogle Scholar
  31. Netsch, T. (1996). Detection of microcalcification clusters in digital mammograms: A scale-space approach. In Doi, K., Giger, M. L., Nishikawa, R. M., and Schmidt, R. A., editors, Digital Mammography ’96, pages 301–306. Elsevier Science, Amsterdam.Google Scholar
  32. Press, W. H., Teukolsky, S. A., Vettering, W. T., and Flannery, B. P., editors (1992). Numerical Recipes in C: The Art of Scientific Computing, 2nd ed. Cambridge University Press.Google Scholar
  33. Schmidt, R. A. and Nishikawa, R. M. (1994). Digital screening mammography. Principles Practice of Oncology, 8:1–16.Google Scholar
  34. Shen, L., Rangayyan, R. M., and Desautels, J. E. L. (1994). Application of shape analysis to mammographic calcifications. IEEE Transactions on Medical Imaging, 13:263–274.CrossRefGoogle Scholar
  35. Sickels, E. A. (1986). Mamnographic features of 300 consecutive noninvasive breast cancers. Am. J. Radiol., 146:661–663.Google Scholar
  36. Sonka, M., Hlavac, V., and Boyle, R. (1998). Image processing, analysis and machine vision, 2nd Ed. Chapman S Hall Computing.Google Scholar
  37. Strickland, R. N. and Hahn, H. I. (1996). Wavelet transform for detecting microcalcifications in mammograms. IEEE Transactions on Medical Imaging, 15:218–229.CrossRefGoogle Scholar
  38. Strickland, R. and Hahn, H. (1997). Wavelet transform methods for object detection and recovery. IEEE Transactions on Image Processing, 6:724–735.CrossRefGoogle Scholar
  39. Thevenaz, P. and Unser, M. (1998). A pyramid approach to subpixel registration based on intensity. IEEE Transactions on Image Processing, 7:27–41.CrossRefGoogle Scholar
  40. Wang, T. C. and Karayiannis, N. B. (1998). Detection of microcalcifications in digital mammogram using wavelets. IEEE Transactions on Medical Imaging, 17:498–509.CrossRefGoogle Scholar
  41. Wickerhauser, M. (1994). Adapted Wavelet Analysis from Theory and Software. A K Peters, Wellesley, Massachusetts.Google Scholar
  42. Xu, X. and Doi, K. (1996). Image feature analysis for computer-aided diagnosis: Detection of right and left hemidiaphragm edges and deliniation of lung field in chest radiographs. Med Phys, 23:1613–1624.CrossRefGoogle Scholar
  43. Yoshida, H. (1998a). Matching pursuit with optimally weighted wavelet packets for extraction of microcalcifications in mammograms. Applied Signal Processing, 5:127–141.CrossRefGoogle Scholar
  44. Yoshida, H. (1998b). Removal of normal anatomic structures in radiographs using wavelet-based non-linear variational method for image matching. Proc SPIE, 3458:174–181.CrossRefGoogle Scholar
  45. Yoshida, H. (1999). Multiresolution non-rigid image registration method and its application to removal of normal anatomic structures in chest radiographs. Proc IEEE International Conference on Image Processing, ICIP99:27AP4.11.Google Scholar
  46. Yoshida, H. (2001). Local contralateral subtraction based on simultaneous segmentation and registration method for computerized detection of pulmonary nodules. Proc SPIE (to appear).Google Scholar
  47. Yoshida, H. and Amit, Y. (2000). Computer-aided diagnosis in chest radiographs: Reduction of false positives by removal of normal anatomic structures based on symmetry between left and right lung regions. Medical Physics (accepted).Google Scholar
  48. Yoshida, H. and Doi, K. (2000). Computerized detection of pulmonary nodules in chest radiographs: Reduction of false positives based on bilateral symmetry of lungs. Proc SPIE, 3979:97–102.CrossRefGoogle Scholar
  49. Yoshida, H., Doi, K., and MacMahon, H. (2000). Computerized detection of pulmonary nodules in chest radiographs: Reduction of false positives based on radiologists’ visual analysis strategy. Proc CARSComputer Assisted Radiology and Surgery, pages 809–813.Google Scholar
  50. Yoshida, H., Doi, K., and Nishikawa, R. M. (1994). Automated detection of clustered microcalcifications in digital mammograms using wavelet transform techniques. Proc SPIE, 2167:868–886.CrossRefGoogle Scholar
  51. Yoshida, H., Doi, K., and Nishikawa, R. M. (1999a). Computer-aided diagnosis in sonography, chest radiography, and mammography based on wavelet transforms. Proc International Meeting on Nuclear Energy in Medicine and Other Peaceful Applications, pages 158–170.Google Scholar
  52. Yoshida, H., Doi, K., Nishikawa, R. M., and Giger, M. L. (1995). Optimizing wavelet transform based on supervised learning for detection of microcalcifications in digital mammograms. Proc. International Conference on Image Processing (ICIP) ’95, ICIP95:152–155.CrossRefGoogle Scholar
  53. Yoshida, H., Doi, K., Nishikawa, R. M., and Giger, M. L. (1996a). Computer-aided diagnosis in mammography: Detection of clustered microcalcifications based on multiscale edge representation. Proc CAR Computer Assisted Radiology, pages 390–395.Google Scholar
  54. Yoshida, H., Doi, K., Nishikawa, R. M., and Giger, M. L. (1996b). True/false signal separation by wavelet packets for detection of microcalcifications in mammograms. Proc SPIE, 2825:805–811.CrossRefGoogle Scholar
  55. Yoshida, H., Doi, K., Nishikawa, R. M., Giger, M. L., and Schmidt, R. A. (1996c). An improved computer-assisted diagnosis schene using wavelet transform for detection of clustered microcalcifications in digital mammograms. Academic Radioloqy, 3:621–627.CrossRefGoogle Scholar
  56. Yoshida, H., Katsuragawa, S., Amit, Y., and Doi, K. (1999b). Waveletbased deformable contour and its application to detection of pulmonary nodules on chest radiographs. In Ritter, G. X., editor, Mathematical Imaging and Vision, volume 8. The International Society for Optical Engineering.Google Scholar
  57. Yoshida, H. and Keserci, B. (2000). Bayesian wavelet snake model for computer-aided diagnosis of lung nodules in chest radiographs. Journal of Integrated Computer-Aided Engineering (Special issue on industrial applications of the wavelet transforms), 7:253–269.Google Scholar
  58. Yoshida, H., Nishikawa, R. M., Giger, M. L., and Doi, K. (1996d). Optimally weighted wavelet packet transform for detection of clustered microcalcifications in digital mammograms. Digital Mammography ’96, pages 317–322.Google Scholar
  59. Zhang, W., Doi, K., Giger, M. L., Nishikawa, R. M., and Schmidt, R. A. (1996). An improved shift-invariant artificial neural network for computerized detection of clustered microcalcifications in digital mammograms. Med Phys, 23:595–601.CrossRefGoogle Scholar
  60. Zhang, W., Yoshida, H., Nishikawa, R. M., and Doi, K. (1998). Optimally weighted wavelet transform based on supervised training for detection of microcalcifications in digital mammograms. Medical Physics, 25:949–956.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2001

Authors and Affiliations

  • Hiroyuki Yoshida
    • 1
  1. 1.Department of RadiologyThe University of ChicagoChicagoUSA

Personalised recommendations