Uso del aprendizaje automático en el diagnóstico del melanoma. Limitaciones por superar

Abstract

BackgroundAutomated image classification is a promising branch of machine learning (ML) useful for skin cancer diagnosis, but little has been determined about its limitations for general usability in current clinical practice. ObjectiveTo determine limitations in the selection of skin cancer images for ML analysis, particularly in melanoma. MethodsRetrospective cohort study design, including 2,849 consecutive high-quality dermoscopy images of skin tumors from 2010 to 2014, for evaluation by a ML system. Each dermoscopy image was assorted according to its eligibility for ML analysis. ResultsOf the 2,849 images chosen from our database, 968 (34%) met the inclusion criteria for analysis by the ML system. Only 64.7% of nevi and 36.6% of melanoma met the inclusion criteria. Of the 528 melanomas, 335 (63.4%) were excluded. An absence of normal surrounding skin (40.5% of all melanomas from our database) and absence of pigmentation (14.2%) were the most common reasons for exclusion from ML analysis. DiscussionOnly 36.6% of our melanomas were admissible for analysis by state-of-the-art ML systems. We conclude that future ML systems should be trained on larger datasets which include relevant non-ideal images from lesions evaluated in real clinical practice. Fortunately, many of these limitations are being overcome by the scientific community as recent works show.