Detection of Skin Erythema in Darkly Pigmented Skin Using Multispectral Images

OBJECTIVE: To develop a technique using a fixed, discrete set of wavelengths that can detect erythema in persons with darkly pigmented skin. The resulting erythema detection approach will then be incorporated into a handheld, point-of-care device that is clinically viable and affordable. DESIGN: A multispectral imaging system was used to acquire spectral images of induced erythema. Individual images were combined into a single image using different fusion algorithms. Image fusion algorithms based on published literature and using linear and nonlinear color space transformation were tested to optimize the contrast between erythematic and uninvolved skin. SETTING: A research laboratory at Georgia Institute of Technology, Atlanta, Georgia. PARTICIPANTS: Fifty-six subjects, of whom 28 had darkly pigmented skin, were recruited from a pool of students, faculty, and staff. MAIN OUTCOME MEASURES: The ability of detection algorithms to detect erythema was measured using Weber contrast. A simple threshold classifier determined accuracy, sensitivity, and specificity for each algorithm. MAIN RESULTS: Four algorithms enhanced contrast of erythema by an order of magnitude over that of a digital photograph. The accuracy of the detection algorithms ranged from 66% to 95%. Sensitivity and specificity ranged from 0% to 100%. One fusion algorithm exhibited an accuracy of more than 90% and sensitivity and specificity of more than 90%. CONCLUSION: The results indicate that erythema in different skin tones can be identified using 2 to 3 filters. Increasing accuracy and discrimination will be targeted via use of filters with narrower half-wave bandwidths, more consistent camera lighting, and improved machine vision techniques.

[1]  Stephen Sprigle,et al.  Characterizing reactive hyperemia via tissue reflectance spectroscopy in response to an ischemic load across gender, age, skin pigmentation and diabetes. , 2002, Medical engineering & physics.

[2]  Guillermo Sapiro,et al.  Segmenting skin lesions with partial-differential-equations-based image processing algorithms , 2000, IEEE Transactions on Medical Imaging.

[3]  J. Parrish,et al.  QUANTITATIVE EVALUATION OF ULTRAVIOLET INDUCED ERYTHEMA , 1983, Photochemistry and photobiology.

[4]  J. Robson,et al.  Application of fourier analysis to the visibility of gratings , 1968, The Journal of physiology.

[5]  S Hagisawa,et al.  Assessment of skin blood content and oxygenation in spinal cord injured subjects during reactive hyperemia. , 1994, Journal of rehabilitation research and development.

[6]  M. Nischik,et al.  Analysis of skin erythema using true-color images , 1997, IEEE Transactions on Medical Imaging.

[7]  J. Eisenberg.  Agency for Health Care Policy and Research. , 1999, Medical care.

[8]  J. L. van Genderen,et al.  Image fusion : issues, techniques and applications , 1994 .

[9]  David A. Landgrebe,et al.  A model-based mixture-supervised classification approach in hyperspectral data analysis , 2002, IEEE Trans. Geosci. Remote. Sens..

[10]  S Sprigle,et al.  Testing the validity of erythema detection algorithms. , 2001, Journal of rehabilitation research and development.

[11]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[12]  Ilias Maglogiannis,et al.  An integrated computer supported acquisition, handling, and characterization system for pigmented skin lesions in dermatological images , 2005, IEEE Transactions on Information Technology in Biomedicine.

[13]  J. Feather,et al.  An investigation of factors affecting the accuracy of in vivo measurements of skin pigments by reflectance spectrophotometry , 1990, Physics in medicine and biology.

[14]  B L Diffey,et al.  Quantitative aspects of ultraviolet erythema. , 1991, Clinical physics and physiological measurement : an official journal of the Hospital Physicists' Association, Deutsche Gesellschaft fur Medizinische Physik and the European Federation of Organisations for Medical Physics.

[15]  D. J. Ellis,et al.  Reflectance spectrophotometric quantification of skin colour changes induced by topical corticosteroid preparations , 1982, The British journal of dermatology.

[16]  Christine Pohl,et al.  Multisensor image fusion in remote sensing: concepts, methods and applications , 1998 .

[17]  C I Chang,et al.  A feasibility study of multispectral image analysis of skin tumors. , 2000, Biomedical instrumentation & technology.

[18]  William V. Stoecker,et al.  Unsupervised color image segmentation: with application to skin tumor borders , 1996 .

[19]  P. Chavez,et al.  STATISTICAL METHOD FOR SELECTING LANDSAT MSS RATIOS , 1982 .

[20]  Y. R. Chen,et al.  USE OF HYPER– AND MULTI–SPECTRAL IMAGING FOR DETECTION OF CHICKEN SKIN TUMORS , 2000 .

[21]  D. J. Ellis,et al.  A theoretical and experimental study of light absorption and scattering by in vivo skin. , 1980, Physics in medicine and biology.

[22]  M Ferguson-Pell,et al.  An empirical technique to compensate for melanin when monitoring skin microcirculation using reflectance spectrophotometry. , 1995, Medical engineering & physics.

[23]  S Sprigle,et al.  Draft definition of stage I pressure ulcers: inclusion of persons with darkly pigmented skin. NPUAP Task Force on Stage I Definition and Darkly Pigmented Skin. , 1997, Advances in wound care : the journal for prevention and healing.