Malignant melanoma (MM) is in the background of the majority of skin cancer-related mortality. On the other hand, seborrheic keratosis (SK) is a common benign lesion that in certain cases can mimic MM. In this work, we utilized a multispectral imaging device prototype with LED illumination to differentiate MM from SK, with the use of 405 nm autofluorescence and 525 and 660 nm diffuse reflectance imaging. Intensity descriptors of the captured images were analyzed, including the ratios, standard deviation and minimum and maximum of intensity values of the lesions in the investigated channels. Particle analysis was performed to assess characteristic patterns of the lesions. Significantly higher intensity values were found in SKs compared to MMs, especially on the autofluorescence images. In addition, significantly more particles with high fluorescence were found in the SK lesions. Based on these results, we created a novel algorithm that provides a parameter, the SK index, that can distinguish MM from SK with a sensitivity of 91.9% and specificity of 57.0%. Based on our findings, this algorithm may be introduced in the clinical practice as a screening method to differentiate MM from SK based on the assessment of autofluorescence and diffuse reflectance imaging.

ESDR479 - Introduction of a Novel Multispectral Imaging Screening Algorithm to Distinguish Malignant Melanoma from Seborrheic Keratosis

The scientific meeting of the European Society for Dermatological Research (ESDR) is held yearly, usually in September. With an international attendance of more than 1000 skin scientists from around the globe, the four-day event includes short oral presentations from peer-reviewed abstracts, keynote lectures from international experts, sponsored symposia, satellite programs, educational events as well as an important focus on posters, networking and building collaborations amongst scientists. For more information about this year’s meeting visit our website.