Fusion of Colour and Depth Information to Enhance Wound Tissue Classification
Patients with diabetes are susceptible to chronic foot
wounds which may be difficult to manage and slow to heal.
Diagnosis and treatment currently rely on the subjective judgement of
experienced professionals. An objective method of tissue assessment
is required. In this paper, a data fusion approach was taken to wound
tissue classification. The supervised Maximum Likelihood and
unsupervised Multi-Modal Expectation Maximisation algorithms
were used to classify tissues within simulated wound models by
weighting the contributions of both colour and 3D depth information.
It was found that, at low weightings, depth information could show
significant improvements in classification accuracy when compared
to classification by colour alone, particularly when using the
maximum likelihood method. However, larger weightings were
found to have an entirely negative effect on accuracy.
[1] S. Stremitzer, T. Wild and T. Hoelzenbein, "How precise is the evaluation of chronic wounds by health care professionals?" Int Wound
J; vol 4(2): pp. 156-61, 2007.
[2] X. Liu, W. Kim, R. Schmidt, B. Drerup and J. Song, "Wound measurement by curvature maps: a feasibility study." Physiol Meas; vol
27(11): pp. 1107-23, 2006.
[3] M. Flanagan, "Wound measurement: Can it help us to monitor progression to healing?" J Wound Care; vol 12(5): pp. 189-94, 2003.
[4] P.C. Matthews, A.R. Berendt and B.A. Lipsky, "Clinical management of
diabetic foot infection: diagnostics, therapeutics and the future." Expert
Rev Anti Infect Ther; vol 5(1): pp. 117-27, 2007.
[5] D.G. Armstrong and B.A. Lipsky, "Diabetic foot infections: stepwise
medical and surgical management." Int Wound J; vol 1(2): pp. 123-32,
2004.
[6] M.J. Levy and J. Valabhji, "The diabetic foot." Surgery (Oxford); vol
22(12): pp. 338-41, 2004.
[7] E.S. Papazoglou, L. Zubkov, X Mao, M. Neidrauer, N. Rannou and
M.S. Weingarten. "Image analysis of chronic wounds for determining
the surface area." Wound Repair Regen; vol 18(4): pp. 349-58, 2010.
[8] J. Shaw, C.M. Hughes, K.M. Lagan, P.M. Bell and M.R. Stevenson, "An
evaluation of three wound measurement techniques in diabetic foot
wounds." Diabetes Care; vol 30(10): pp. 2641-2, 2007.
[9] R.J. Winder, T.A. Darvann, W. McKnight, J.D. Magee and P. Ramsay-
Baggs, "Technical validation of the Di3D stereophotogrammetry surface
imaging system." Br J Oral Maxillofac Surg; vol 46(1): pp. 33-7, 2008.
[10] B. Khambay, N. Nairn, A. Bell, J. Miller, A. Bowman and A.F. Ayoub,
"Validation and reproducibility of a high-resolution three-dimensional
facial imaging system." Br J Oral Maxillofac Surg; vol 46(1): pp. 27-32,
2008.
[11] D.P. Thompson, J.H Cundell, D.A. McDowell and R.J. Winder,
"Simulated wound volume measurement using 3D
stereophotogrammetry." Proc. 14th annual Irish Machine Vision and
Image Processing (IMVIP) Conference, Limerick, 2010, pp. 30-43.
[12] D.L. Pham, C. Xu and J.L. Prince, "Current Methods in Medical Image
Segmentation." Annual Review of Biomedical Engineering, vol 2(1), pp.
315-337, 2000.
[13] R.O. Duda, P.E. Hart and D.G. Stork. Pattern Classification, 2nd Edn,
2001. New York: John Wiley & Sons.
[14] H. Wannous, Y. Lucas, S. Treuillet and B. Albouy. "A complete 3D
wound assessment tool for accurate tissue classification and
measurement." 15th IEEE International Conference on Image
Processing, 2008; pp. 2928-31.
[15] H. Wannous, Y. Lucas and B. Albouy. "Enhanced assessment of the
wound-healing process by accurate multiview tissue classification."
IEEE Transactions on Medical Imaging; pp. 315-26, 2011.
[16] Y.J. Zhang, "A review of recent evaluation methods for image
segmentation", Signal Processing and its Applications, Sixth
International, Symposium on; pp. 148-51, 2001.
[17] X. Hong, S.I. McClean, B. Scotney and P.J. Morrow, "Model-based
Segmentation of Multimodal Images", Lecture Notes in Computer
Science, vol 4673, pp. 604-61, 2007.
[18] C. Fraley and A.E. Raftery, "How many clusters? Which clustering
method? Answers via model-based cluster analysis." The Computer
Journal; vol 41(8): pp. 578-88, 1998.
[19] B. Al Momani, "Classification of Remotely Sensed Imagery Using a
Knowledge-Based Approach." PhD thesis, University of Ulster, 2008.
[1] S. Stremitzer, T. Wild and T. Hoelzenbein, "How precise is the evaluation of chronic wounds by health care professionals?" Int Wound
J; vol 4(2): pp. 156-61, 2007.
[2] X. Liu, W. Kim, R. Schmidt, B. Drerup and J. Song, "Wound measurement by curvature maps: a feasibility study." Physiol Meas; vol
27(11): pp. 1107-23, 2006.
[3] M. Flanagan, "Wound measurement: Can it help us to monitor progression to healing?" J Wound Care; vol 12(5): pp. 189-94, 2003.
[4] P.C. Matthews, A.R. Berendt and B.A. Lipsky, "Clinical management of
diabetic foot infection: diagnostics, therapeutics and the future." Expert
Rev Anti Infect Ther; vol 5(1): pp. 117-27, 2007.
[5] D.G. Armstrong and B.A. Lipsky, "Diabetic foot infections: stepwise
medical and surgical management." Int Wound J; vol 1(2): pp. 123-32,
2004.
[6] M.J. Levy and J. Valabhji, "The diabetic foot." Surgery (Oxford); vol
22(12): pp. 338-41, 2004.
[7] E.S. Papazoglou, L. Zubkov, X Mao, M. Neidrauer, N. Rannou and
M.S. Weingarten. "Image analysis of chronic wounds for determining
the surface area." Wound Repair Regen; vol 18(4): pp. 349-58, 2010.
[8] J. Shaw, C.M. Hughes, K.M. Lagan, P.M. Bell and M.R. Stevenson, "An
evaluation of three wound measurement techniques in diabetic foot
wounds." Diabetes Care; vol 30(10): pp. 2641-2, 2007.
[9] R.J. Winder, T.A. Darvann, W. McKnight, J.D. Magee and P. Ramsay-
Baggs, "Technical validation of the Di3D stereophotogrammetry surface
imaging system." Br J Oral Maxillofac Surg; vol 46(1): pp. 33-7, 2008.
[10] B. Khambay, N. Nairn, A. Bell, J. Miller, A. Bowman and A.F. Ayoub,
"Validation and reproducibility of a high-resolution three-dimensional
facial imaging system." Br J Oral Maxillofac Surg; vol 46(1): pp. 27-32,
2008.
[11] D.P. Thompson, J.H Cundell, D.A. McDowell and R.J. Winder,
"Simulated wound volume measurement using 3D
stereophotogrammetry." Proc. 14th annual Irish Machine Vision and
Image Processing (IMVIP) Conference, Limerick, 2010, pp. 30-43.
[12] D.L. Pham, C. Xu and J.L. Prince, "Current Methods in Medical Image
Segmentation." Annual Review of Biomedical Engineering, vol 2(1), pp.
315-337, 2000.
[13] R.O. Duda, P.E. Hart and D.G. Stork. Pattern Classification, 2nd Edn,
2001. New York: John Wiley & Sons.
[14] H. Wannous, Y. Lucas, S. Treuillet and B. Albouy. "A complete 3D
wound assessment tool for accurate tissue classification and
measurement." 15th IEEE International Conference on Image
Processing, 2008; pp. 2928-31.
[15] H. Wannous, Y. Lucas and B. Albouy. "Enhanced assessment of the
wound-healing process by accurate multiview tissue classification."
IEEE Transactions on Medical Imaging; pp. 315-26, 2011.
[16] Y.J. Zhang, "A review of recent evaluation methods for image
segmentation", Signal Processing and its Applications, Sixth
International, Symposium on; pp. 148-51, 2001.
[17] X. Hong, S.I. McClean, B. Scotney and P.J. Morrow, "Model-based
Segmentation of Multimodal Images", Lecture Notes in Computer
Science, vol 4673, pp. 604-61, 2007.
[18] C. Fraley and A.E. Raftery, "How many clusters? Which clustering
method? Answers via model-based cluster analysis." The Computer
Journal; vol 41(8): pp. 578-88, 1998.
[19] B. Al Momani, "Classification of Remotely Sensed Imagery Using a
Knowledge-Based Approach." PhD thesis, University of Ulster, 2008.
@article{"International Journal of Medical, Medicine and Health Sciences:64089", author = "Darren Thompson and Philip Morrow and Bryan Scotney and John Winder", title = "Fusion of Colour and Depth Information to Enhance Wound Tissue Classification", abstract = "Patients with diabetes are susceptible to chronic foot
wounds which may be difficult to manage and slow to heal.
Diagnosis and treatment currently rely on the subjective judgement of
experienced professionals. An objective method of tissue assessment
is required. In this paper, a data fusion approach was taken to wound
tissue classification. The supervised Maximum Likelihood and
unsupervised Multi-Modal Expectation Maximisation algorithms
were used to classify tissues within simulated wound models by
weighting the contributions of both colour and 3D depth information.
It was found that, at low weightings, depth information could show
significant improvements in classification accuracy when compared
to classification by colour alone, particularly when using the
maximum likelihood method. However, larger weightings were
found to have an entirely negative effect on accuracy.", keywords = "Classification, data fusion, diabetic foot,stereophotogrammetry, tissue colour.", volume = "6", number = "11", pages = "616-6", }
