Skin lesion classification based on in vitro Raman spectroscopy is approached using a nonlinear neural network classifier. The classification framework is probabilistic and highly automated. The framework includes a feature extraction for Raman spectra and a fully adaptive and robust feedforward neural network classifier. Moreover, classification rules learned by the neural network may be extracted and evaluated for reproducibility, making it possible to explain the class assignment. The classification performance for the present data set, involving 222 cases and five lesion types, was 80.5%/spl plusmn/5.3% correct classification of malignant melanoma, which is similar to that of trained dermatologists based on visual inspection. The skin cancer basal cell carcinoma has a classification rate of 95.8%/spl plusmn/2.7%, which is excellent. The overall classification rate of skin lesions is 94.8%/spl plusmn/3.0%. Spectral regions, which are important for network classification, are demonstrated to reproduce. Small distinctive bands in the spectrum, corresponding to specific lipids and proteins, are shown to hold the discriminating information which the network uses to diagnose skin lesions.
1 February 2010 in Journal of Investigative Dermatology
UVB radiation increases serum vitamin D level expressed as 25-hydroxyvitamin-D3 (25(OH)D), but the influence of skin pigmentation, baseline 25(OH)D level, and total cholesterol has not been well characterized. To determine the importance of skin pigmentation, baseline 25(OH)D level, and total cholesterol on 25(OH)D production after UVB exposure, 182 persons were screened for 25(OH)D level. A total of 50 participants with a wide range in baseline 25(OH)D levels were selected to define the importance of baseline 25(OH)D level. Of these, 28 non-sun worshippers with limited past sun exposure were used to investigate the influence of skin pigmentation and baseline total cholesterol. The participants had 24% of their skin exposed to UVB (3 standard erythema doses) four times every second or third day. Skin pigmentation and 25(OH)D levels were measured before and after the irradiations. Total cholesterol was measured at baseline. The increase in 25(OH)D level after UVB exposure was negatively correlated with baseline 25(OH)D level (P<0.001) and positively correlated with baseline total cholesterol level (P=0.005), but no significant correlations were found with constitutive or facultative skin pigmentation. In addition, we paired a dark-skinned group with a fair-skinned group according to baseline 25(OH)D levels and found no differences in 25(OH)D increase after identical UVB exposure.
To assess individual time-related (time-stamped) UV radiation (UVR) dose pattern and sun exposure behavior. Open prospective observational study. University hospital. Study Subjects Two hundred eighty-five Danish volunteers with apparently healthy skin: children, adolescents, indoor workers, sun worshippers, golfers, and gardeners (age range, 4-68 years). Measurements We developed a personal electronic UVR dosimeter in a wristwatch (SunSaver) and measured continuously time-related UVR doses in standard erythema dose (SED) and corresponding sun exposure behavior from diaries, resulting in 346 sun-years (median, 119 days). The estimated yearly UVR doses were calculated based on personal and ambient measured doses. The median estimated yearly UVR dose was 173 SEDs (range, 132 SEDs [indoor workers]-224 SEDs [gardeners]), with no significant difference by age (P =.25) or sex (P =.75). The SED of girls (175 SEDs) was significantly (P =.04) higher than that of boys (116 SEDs). Subjects younger than 20 years had an increase of 5 SEDs per year (P =.03). Sunbathing or exposing shoulders (risk behavior) outside the beach resulted in a median of 2.5 SEDs per day in northern Europe and 3.2 SEDs per day in southern Europe; however, at the beach, corresponding values were 4.6 and 6.9 SEDs per day. Children and adolescents received more than half their total UVR dose at the beach. Sunburning doses above 10 SEDs per day were connected with sunbathing or exposing shoulders. Of the UVR dose, 50% was received between noon and 3 PM. Only the gardeners received most of their UVR dose (55%) on working days. High UVR doses are connected with risk behavior, except for outdoor workers. There is no need to change sun exposure habits on days without risk behavior.
About Me
Department of Dermatology
Bispebjerg University Hospital
Copenhagen, Denmark
Department of Dermatology
Bispebjerg University Hospital
Copenhagen, Denmark