Can self-training identify suspicious ugly duckling lesions?
This addresses the need for standardized melanoma detection in dermatology, though it is incremental by applying existing self-supervised methods to a specific clinical challenge.
The paper tackled the problem of automatically detecting suspicious 'ugly duckling' skin lesions, which differ from other lesions on a patient, using self-supervised machine learning to identify outliers, achieving a sensitivity of 72.1% and diagnostic accuracy of 94.2% compared to dermatologists.
One commonly used clinical approach towards detecting melanomas recognises the existence of Ugly Duckling nevi, or skin lesions which look different from the other lesions on the same patient. An automatic method of detecting and analysing these lesions would help to standardize studies, compared with manual screening methods. However, it is difficult to obtain expertly-labelled images for ugly duckling lesions. We therefore propose to use self-supervised machine learning to automatically detect outlier lesions. We first automatically detect and extract all the lesions from a wide-field skin image, and calculate an embedding for each detected lesion in a patient image, based on automatically identified features. These embeddings are then used to calculate the L2 distances as a way to measure dissimilarity. Using this deep learning method, Ugly Ducklings are identified as outliers which should deserve more attention from the examining physician. We evaluate through comparison with dermatologists, and achieve a sensitivity rate of 72.1% and diagnostic accuracy of 94.2% on the held-out test set.