Medical and Biological Engineering and Computing

, Volume 42, Issue 6, pp 777–786 | Cite as

New hybrid stochastic-deterministic technique for fast registration of dermatological images

Article
Received:
Accepted:

Abstract

Digital image processing in the medical field has become very popular in recent years owing to the significant advantages it offers over conventional techniques of visual or analogue image analysis. One of the most significant aspects in medical image processing has been that of image registration, which deals with the task of registering two images taken under different conditions. Image registration is considered an important issue in the field of dermatology, as pictures of a lesion taken in different periods need to be compared and quantitatively analysed. A hybrid image registration scheme was developed and evaluated for dermatological applications. The method splits the parameter estimation problem into two, with a combination of deterministic and iterative estimation techniques. The scaling and rotation parameters are estimated using a cross-correlation of image invariant image descriptors algorithm, whereas the two translation parameters are estimated with a non-parametric similarity criterion and a hill-climbing optimisation scheme. The efficacy of the method has been validated for the registration and comparison of malignant melanoma images. Determination of rotation and scaling parameters was performed using the log-polar transformation technique, which proved to be very accurate, even when high rotation and scaling values were imposed. Deviations for the rotation parameter estimations were less than 0.5%, whereas, for the scaling factor, differences were on average less than 2.5%, with a maximum difference estimated to be 4.5%. Translation parameter estimation was performed using integer similarity measures namely the stochastic sign change, the deterministic sign change (DSC) and the window value range, the performance of which has been assessed and, in all cases, was found to be highly effective. A novel hill-climbing optimisation algorithm has been proposed and, in combination with the DSC similarity criterion, was evaluated and proved to successfully estimate translation parameters. Thus the proposed hybrid registration technique can successfully estimate problem parameters in a time-efficient manner.

Keywords

Medical imaging Image registration Dermatological applications 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. American Cancer Society (2004): ‘Cancer reference information’. Available at http: //www.cancer.org/docroot/CRI/CRI_2.asp (last accessed 1 July, 2004)Google Scholar
  2. Barnea, D. I., andSilverman, H. F. (1972): ‘A class of algorithms for fast digital image registration’,IEEE Trans. Comput.,21, pp. 179–186Google Scholar
  3. Bekey, G. A., andMasri, S. F. (1983): ‘Random search techniques for optimization of nonlinear systems with many parameter’,Math. Comput. Simul.,25, pp. 210–213CrossRefGoogle Scholar
  4. Brown, L. G. (1992): ‘A survey of image registration techniques’,ACM Comput. Surv.,24, pp. 325–376CrossRefGoogle Scholar
  5. Chen, H., Varshney, P. K., andArora, M. K. (2003): ‘Performance of mutual information similarity measure for registration of multitemporal remote sensing images’,IEEE Trans. Geosci. Remote Sens.,41, pp. 2445–2454Google Scholar
  6. Chiang, J. Y., andSullivan, B. J. (1993): ‘Coincident bit counting—A new criterion for image registration’,IEEE Trans. Med. Imag.,12, pp. 30–38Google Scholar
  7. Cideciyan, A. V. (1995): ‘Registration of ocular fundus images, an algorithm using cross-correlation of triple invariant image descriptors’,IEEE Eng. Med. Biol.,14, pp. 52–58Google Scholar
  8. Ganster, H., Pinz, A., Rohrer, R., Wildling, E., Binder, M., andKittler, H. (2001): ‘Automated melanoma recognition’,IEEE Trans. Med. Imag.,20, pp. 233–239Google Scholar
  9. Gonzales, R. C., andWoods, R. E. (1993): ‘Digital image processing’ (Addison-Wesley, Reading, Massachusetts, 1993)Google Scholar
  10. Hill, D. L. G., Batchelor, P. G., Holden, M., andHawkes, D. (2001). ‘Medical image registration’,Phys. Med. Biol.,46, pp. R1-R45CrossRefGoogle Scholar
  11. Horn, B. K. P. (1986): ‘Robot vision’ (The MIT Press, 1986)Google Scholar
  12. Hsu, L., Loew, H. M., andOstuni, J. (1999): ‘Multimodality image registration based on hierarchical shape representation’,Proc. SPIE-Int. Soci. Opt. Eng.,3661, pp. 811–818Google Scholar
  13. Jemal, A., Tiwari, R. C., Murray, T. et al. (2004): ‘Cancer statistics, 2004’,CA Cancer J. Clin.,54, pp. 8–29Google Scholar
  14. Laliberte, F., Gagnon, L., andSheng, Y. (2003): ‘Fusion of retinal images—an evaluation study’,IEEE Trans. Med. Imag.,22, pp. 661–673Google Scholar
  15. Maintza, J. B. A., Viergever, M. A. (1998): ‘A survey of medical image registration’,Med. Image Anal.,2, pp. 1–36Google Scholar
  16. McGregor, B. (1998): ‘Automatic registration of images of pigmented skin lesions’,Pattern Recognit.,31, pp. 805–817CrossRefGoogle Scholar
  17. Penney, G. P., Wesse, J., Little, J. A.,et al. (1998): ‘A comparison of similarity measures for use in 2-D-3-D medical image registration’,IEEE Trans. Med. Imag.,17, pp. 586–595Google Scholar
  18. Perednia, D. A., andWhite, R. G. (1992): ‘Automatic registration of multiple skin lesions by use of point pattern matching’,Comput. Med. Imag. Graph.,16, pp. 205–216CrossRefGoogle Scholar
  19. Pratt, K. (1974): ‘Correlation techniques of image registration’,IEEE Trans. Aerosp. Electron. Syst.,10, pp. 353–358Google Scholar
  20. Roning, J., andRiech, M. (1998): ‘Registration of nevi in successive skin images for early detection of melanoma. Proc. 14th Int. Conf. on Pattern Recognition,1, pp. 352–357Google Scholar
  21. Schmid-Saugeon, Guillod, J., andThiran, J. P. (2003): ‘Towards a computer-aided diagnosis system for pigmented skin lesions’,Comput. Med. Imag. Graph.,27, pp. 65–78Google Scholar
  22. Shekhar, R., Zagrodsky, V., Castro-Pareja, C. R., Walimbe, V., andJagadeesh, J. M. (2003) ‘High-speed registration of three- and four-dimensional medical images by using voxel similarity’,Radiographics,23, pp. 1673–1681Google Scholar
  23. Svedlow, M., McGillem, C. D., andAnuta, P. E. (1979): ‘Image registration: similarity measure and preprocessing method comparisons’,IEEE Trans. Aerosp. Electron. Syst.,14, pp. 141–149Google Scholar
  24. Venot, A., andLeclerc, V. (1984): ‘Automated correlation of patient motion and gray values prior to subtraction in digitized angiography’,IEEE Trans. Med. Imag.,3, pp. 179–186Google Scholar
  25. Venot, A., Lebruchec, J. F., andRoucayrol, J. C. (1984): ‘A new class of similarity measures for robust image registration’,Comput. Vision, Graph. Image Process.,28, pp. 176–184Google Scholar
  26. Venot, A., Devaux, J. Y., Herbin, M., Lebruchec, J. F., Dubertret, L., Raulo, Y., andRoucayrol, J. C. (1988): ‘An automated system for the registration and comparison of photographic images in medicine’,IEEE Trans. Med. Imag.,7, pp. 298–303Google Scholar
  27. Walter, E., Pronzato, L., andVenot, A. (1989): ‘Theoretical properties of sign change criteria for robust off-line estimation’,Automatica,25, pp. 949–952CrossRefGoogle Scholar
  28. White, R. G., andPerednia, D. A. (1992): ‘Automatic derivation of initial match points for paired digital images of skin’,Comput. Med. Imag. Graph.,16, pp. 217–225CrossRefGoogle Scholar
  29. Zitova, B., andFlusser, J. (2003): ‘Image registration methods: a survey’,Image Vis. Comput.,21, pp. 977–1000CrossRefGoogle Scholar

Copyright information

© IFMBE 2004

Authors and Affiliations

  1. 1.Biomedical Engineering Laboratory, School of Electrical & Computer EngineeringNational Technical University of AthensGreece

Personalised recommendations