Automatic differentiation of melanoma from melanocytic nevi with multispectral digital dermoscopy: A feasibility study

Background: Differentiation of melanoma from melanocytic nevi is difficult even for skin cancer specialists. This motivates interest in computer-assis ted analysis of lesion images. Objective: Our purpose was to offer fully automatic differentiation of mela noma from dysplastic and other melanocytic nevi through multispectral digit al dermoscopy. Method: At 4 clinical centers, images were taken of pigmented lesions suspe cted of being melanoma before biopsy Ten gray-level (MelaFind) images of ea ch lesion were acquired, each in a different portion of the visible and nea r-infrared spectrum. The images of 63 melanomas (33 invasive, 30 in situ) a nd 183 melanocytic nevi (of which 111 were dysplastic) were processed autom atically through a computer expert system to separate melanomas from nevi. The expert system used either a linear or a nonlinear classifier. The "gold standard" for training and testing these classifiers was concordant diagno sis by two dermatopathologists. Results: On resubstitution, 100% sensitivity was achieved at 85% specificit y with a W-parameter linear classifier and 100%-/73% with a 12-parameter no nlinear classifier. Under leave-one-out cross-validation, the linear classi fier gave 100%/84% (sensitivity/specificity), whereas the nonlinear classif ier gave 95%/68%. Infrared image features were significant, as were feature s based on wavelet analysis. Conclusion: Automatic differentiation of invasive and in situ melanomas fro m melanocytic nevi is feasible, through multispectral digital dermoscopy.