A deep analysis on high‐resolution dermoscopic image classification

Convolutional neural networks (CNNs) have been broadly employed in dermoscopic image analysis, mainly as a result of the large amount data gathered by International Skin Imaging Collaboration (ISIC). As many other medical imaging domains, state-of-the-art methods take advantage architectures developed for tasks, frequently assuming full transferability between enormous sets natural images (e.g. ImageNet) and images, which is not always case. A comprehensive analysis on effectiveness deep learning techniques when applied to provided. To achieve this goal, authors consider several CNNs analyse how their performance affected size network, resolution, augmentation process, available data, model calibration. Moreover, taking performed, novel ensemble method further increase classification accuracy designed. The proposed solution achieved third best 2019 official ISIC challenge, with an 0.593.