Biometric identification using knee X-rays

Abstract

Identification of people often makes use of unique features of the face, fingerprints and retina. Beyond this, a similar identifying process can be applied to internal parts of the body that are not visible to the unaided eye. Here we show that knee X-rays can be used for the identification of individual persons. The image analysis method is based on the wnd-charm algorithm, which has been found effective for the diagnosis of clinical conditions of knee joints. Experimental results show that the rank-10 identification accuracy using a dataset of 425 individuals is ∼56%, and the rank-1 accuracy is ∼34%. The dataset contained knee X-rays taken several years apart from each other, showing that the identifiable features correspond to specific persons, rather than the present clinical condition of the joint.

References

1. Bolbos, R.I., Zuo, J., Banerjee, S., Link, T.M., Ma, C.B., Li, X. and Majumdar, S. (2008) 'Relationship between trabecular bone structure and articular cartilage morphology and relaxation times in early OA of the knee joint using parallel MRI at 3T', Osteoarthritis Cartilage, In press.
2. Boniatis, I., Costaridou, L., Cavouras, D., Kalatzis, I., Panagiotopoulos, E. and Panayiotakis, G. (2006) 'Osteoarthritis severity of the hip by computer-aided grading of radiographic images', Medical & Biological Engineering & Computing, Vol. 44, pp. 793-803.
3. Boniatis, I., Cavouras, D., Costaridou, L., Kalatzis, I., Panagiotopoulos, E. and Panayiotakis, G. (2007) 'Computer-aided grading and quantification of hip osteoarthritis severity employing shape descriptors of radiographic hip joint space', Computers in Biology and Medicine, Vol. 37, pp. 1786-1795.
4. Lynch, J.A., Hawkes, D.J. and Buckland-Wright, J.C. (1991) 'Analysis of texture in macroradiographs of osteoarthritic knee using the fractal signature', Physics in Medicine and Biology, Vol. 36, pp. 709-722.
5. Messent, E.M., Ward, R.J., Tonkin, C.J. and Buckland-Wright, J.C. (2005) 'Cancellous bone difference between knees with early, definite and advanced joint space loss: a comparative quantitative macroradiographic study', Osteoarthritis Cartilage, Vol. 13, pp. 39-47.
6. Orlov, N., Shamir, L., Johnston, J., Macura, T., Eckley, D.M. and Goldberg, I.G. (2008), 'WND-CHARM: multi-purpose image classification using compound image transforms', Pattern Recognition Letters, Vol. 29, pp. 1684-1693.
7. Podsiadlo, P., Wolski, M.M. and Stachowiak, G.W. (2008a) 'Automated selection of trabecular bone regions in knee radiographs', Medical Physics, Vol. 35, pp. 1870-1883.
8. Podsiadlo, P., Dahl, L., Englund, M., Lohmander, L.S. and Stachowiak, G.W. (2008b) 'Differences in trabecular bone texture between knees with and without radiographic osteoarthritis detected by fractal methods', Osteoarthritis Cartilage, Vol. 16, pp. 323-329.
9. Shamir, L., Orlov, N., Macura, T., Eckley, D.M., Johnston, J. and Goldberg, I.G. (2008) 'Wndchrm - an open source utility for biological image analysis', BMC - Source Code for Biology and Medicine, Vol. 3, p. 13.
10. Shamir, L., Ling, S., Scott, W., Bos, A., Orlov, N., Macura, T., Eckley, D.M. and Goldberg, I.G. (2009) 'Knee X-ray image analysis method for automated detection of Osteoarthritis', IEEE Transactions on Biomedical Engineering, In press.
11. Shock, N.W., Greulich, R.C., Costa, P.T., Jr., Andres, R., Lakatta, E.G., Arenberg, D. and Tobin, J.D. (1984) Normal Human Aging: The Baltimore Longitudinal Study of Aging, NIH Publication No. 84-2450, Government Printing Office, Washington, DC.