Open AccessImpact of various color LED flashlights and different lighting source to skin distances on the manual and the computer‐aided detection of basal cell carcinoma borders
Author(s) -
Bakht Mohamadreza K.,
Pouladian Majid,
Mofrad Farshid B.,
Honarpisheh Hamid
Publication year - 2014
Publication title -
skin research and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.521
H-Index - 69
eISSN - 1600-0846
pISSN - 0909-752X
DOI - 10.1111/srt.12090
Subject(s) - basal cell carcinoma , dermatoscopy , artificial intelligence , computer science , computer vision , basal cell , skin lesion , lesion , skin cancer , computer graphics (images) , medicine , dermatology , pathology , melanoma , cancer , cancer research
Background/aims Quantitative analysis based on digital skin image has been proven to be helpful in dermatology. Moreover, the borders of the basal cell carcinoma ( BCC ) lesions have been challenging borders for the automatic detection methods. In this work, a computer‐aided dermatoscopy system was proposed to enhance the clinical detection of BCC lesion borders. Methods Fifty cases of BCC were selected and 2000 pictures were taken. The lesion images data were obtained with eight colors of flashlights and in five different lighting source to skin distances ( SSD s). Then, the image‐processing techniques were used for automatic detection of lesion borders. Further, the dermatologists marked the lesions on the obtained photos. Results Considerable differences between the obtained values referring to the photographs that were taken at super blue and aqua green color lighting were observed for most of the BCC borders. It was observed that by changing the SSD , an optimum distance could be found where that the accuracy of the detection reaches to a maximum value. Conclusion This study clearly indicates that by changing SSD and lighting color, manual and automatic detection of BCC lesions borders can be enhanced.