Deep-learning approach in the study of skin lesions.

Filipescu, Stefan-Gabriel; Butacu, Alexandra-Irina; Tiplica, George-Sorin; Nastac, Dumitru-Iulian

BACKGROUND Medical technology is far from reaching its full potential. An area that is currently expanding is that of precision medicine. The aim of this article is to present an application of precision medicine-a deep-learning approach to computer-aided diagnosis in the field of dermatology. MATERIALS AND METHODS The main dataset was proposed in the edition of the ISIC Challenge that took place in 2019 and included 25 331 dermoscopic images from eight different categories of lesions-three of them were malignant and five benign. The behavior of the model was also tested on a dataset collected from the second Department of Dermatology, of the Colentina Clinical Hospital. RESULTS The overall accuracy of the model was 78.11%. Of the total 5031 samples included in the test subset, 3958 were correctly classified. The accuracy of the model on the clinical dataset is lower than that obtained in the first instance. CONCLUSION The architecture of the model can be considered of general use, being able to be adapted in an optimal way for a wide range of classifications. The model has achieved performance within the expected limits but can be further improved by new methods.