Leveraging Web Data for Skin Lesion Classification

The success of deep learning is mainly based on the assumption that for the given application, there is access to a large amount of annotated data. In medical imaging applications, having access to a big-well-annotated data-set is restrictive, time-consuming and costly to obtain. Although diverse techniques as data augmentation can be leveraged to increase the size and variability within the data-set, the representativeness of the training set is still limited by the number of available samples. Furthermore, a small-size and well-annotated data-set can not guarantee the generalizability to unseen samples.     «

The success of deep learning is mainly based on the assumption that for the given application, there is access to a large amount of annotated data. In medical imaging applications, having access to a big-well-annotated data-set is restrictive, time-consuming and costly to obtain. Although diverse techniques as data augmentation can be leveraged to increase the size and variability within the data-set, the representativeness of the training set is still limited by the number of available sa...     »