Deep Learning For Skin Cancer Diagnosis With Hierarchical Architectures

Skin lesions are organized in a hierarchical way, which is taken into account by dermatologists when diagnosing them. However, automatic systems do not make use of this information, performing the diagnosis in a one-vs-all approach, where all types of lesions are considered. In this paper we propose to mimic the medical strategy and train a deep-learning architecture to perform a hierarchical diagnosis. Our results highlight the benefits of addressing the classification of dermoscopy images in a structured way. Additionally, we provide an extensive evaluation of criteria that must be taken into account in the development of diagnostic systems based on deep learning.