Haemoglobin distribution in ulcers for healing assessment

Wounds that do not follow a predictable course of healing within a specified period of time develop into ulcers causing severe pain and discomfort to the patients. One of the most prominent changes during wound healing is the colour of the tissues. Describing the tissues in terms of percentages of each tissue colour is an approved clinical method of wound healing assessment. The growth of the red granulation tissue marks the beginning of ulcer healing. Granulation tissue appears red in colour due to haemoglobin content in the blood capillaries. An approach based on utilizing haemoglobin content in chronic ulcers as an image marker to detect the growth of granulation tissue is investigated in this study. Independent Component Analysis is employed to extract grey-level haemoglobin images from RGB colour images of chronic ulcers. Extracted haemoglobin images indicate areas of haemoglobin distribution reflecting detected regions of granulation tissue. Data clustering techniques are implemented to classify and segment detected regions of granulation tissue from the extracted haemoglobin images. Results obtained indicate that the developed algorithm performs fairly well with an average sensitivity of 88.24% and specificity of 98.82% when compared to the dermatologist's assessment. The ultimate aim of this research work is to develop an objective non-invasive wound healing assessment system capable of evaluating the healing status of chronic ulcers in a more precise and reliable way.

[1]  F. Ashcroft,et al.  VIII. References , 1955 .

[2]  J. Winder,et al.  New protocol for leg ulcer tissue classification from colour images , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  Robert J Goldman,et al.  More than One Way to Measure a Wound: An Overview of Tools and Techniques , 2002, Advances in skin & wound care.

[4]  Hazem Wannous,et al.  A complete 3D wound assessment tool for accurate tissue classification and measurement , 2008, 2008 15th IEEE International Conference on Image Processing.

[5]  Hans-Oliver Rennekampff,et al.  Evidence-based Management Strategies for Treatment of Chronic Wounds , 2009, Eplasty.

[6]  K. Stamnes,et al.  The optics of human skin : Aspects important for human health , 2008 .

[7]  Stephen J. Sangwine,et al.  A colour histogram clustering technique for tissue analysis of healing skin wounds , 1997 .

[8]  Norimichi Tsumura,et al.  Independent Component Analysis of Skin Color Image , 1998, CIC.

[9]  R. Anderson,et al.  The optics of human skin. , 1981, The Journal of investigative dermatology.

[10]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .

[11]  Ela Claridge,et al.  From Colour to Tissue Histology: Physics Based Interpretation of Images of Pigmented Skin Lesions , 2002, MICCAI.

[12]  A Venot,et al.  Color quantitation through image processing in dermatology. , 1990, IEEE transactions on medical imaging.

[13]  W. Westerhof,et al.  Image processing in the study of wound healing. , 1995, Clinics in dermatology.

[14]  S. Treuillet,et al.  Supervised Tissue Classification from Color Images for a Complete Wound Assessment Tool , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  A. Venot,et al.  Assessment of healing kinetics through true color image processing , 1993, IEEE Trans. Medical Imaging.

[16]  Glenn Fung,et al.  A Comprehensive Overview of Basic Clustering Algorithms , 2001 .

[17]  Adilson Gonzaga,et al.  Segmentation and analysis of leg ulcers color images , 2001, Proceedings International Workshop on Medical Imaging and Augmented Reality.

[18]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[19]  E. Claridge,et al.  A skin imaging method based on a colour formation model and its application to the diagnosis of pigmented skin lesions , 2002 .

[20]  Ela Claridge,et al.  Developing a predictive model of human skin coloring , 1996, Medical Imaging.